最近 7 天
42
次命中
Keyword Tracking
关键词追踪：agent
这个页面会长期追踪你配置里关心的关键词，并把命中的论文按日期沉淀下来。
最近 30 天
197
次命中
全部历史
448
次命中
近期走势
最近一次命中来自 LM：Joint Learning of Experiential Rules and Policies for Large Language Model Agents
2026-06-15
0
2026-06-16
11
2026-06-17
14
2026-06-18
6
2026-06-19
13
2026-06-20
0
2026-06-21
0
2026-06-22
0
2026-06-23
6
2026-06-24
14
2026-06-25
9
2026-06-26
13
2026-06-27
0
2026-06-28
0
命中明细
按日期回看匹配到这个关键词的论文标题，并保留来源 feed 信息。
2026-06-26
Joint Learning of Experiential Rules and Policies for Large Language Model Agents
For LLM agents in multi-step interactive environments, a key challenge is to make effective use of accumulated interaction experience. Existing work has typically separated two us…
Semantic Early-Stopping for Iterative LLM Agent Loops
Multi-agent large language model (LLM) loops, for example a Writer that drafts and a Critic that revises, are almost always terminated by a fixed iteration cap (max_iterations). T…
When Does Combining Language Models Help? A Co-Failure Ceiling on Routing, Voting, and Mixture-of-Agents Across 67 Frontier Models
Multi-model LLM systems such as routing, voting, cascades, fusion, and mixture-of-agents are used to beat single-model accuracy. We show that their gain is capped by a quantity th…
Improving General Role-Playing Agents via Psychology-Grounded Reasoning and Role-Aware Policy Optimization
Building general-purpose role-playing agents that faithfully portray any character from a natural-language profile remains challenging. The dominant paradigm -- supervised fine-tu…
OpenRCA 2.0: From Outcome Labels to Causal Process Supervision
Root cause analysis (RCA) poses a holistic test of LLM agentic capabilities, such as long-context understanding, multi-step reasoning, and tool use. However, existing datasets suf…
AgentX: Towards Agent-Driven Self-Iteration of Industrial Recommender Systems
Recommendation algorithm iteration is moving from an artisanal, engineer-bound process toward an industrialized research loop, but this transition remains blocked by a structural…
MIRROR: Novelty-Constrained Memory-Guided MCTS Red-Teaming for Agentic RAG
Multimodal agentic retrieval-augmented generation (RAG) systems expand the attack surface beyond prompt injection to include text poisoning, image injection, direct-query attacks,…
To Run or Not to Run: Analyzing the Cost-Effectiveness of Code Execution in LLM-Based Program Repair
LLM-based agents for program repair are increasingly built on a "generate-run-revise" paradigm, iteratively executing tests to evaluate and refine patches. This execution-based ap…
How Much Static Structure Do Code Agents Need? A Study of Deterministic Anchoring
LLM-based code agents navigate repositories through keyword search but miss the structural relationships, such as call graphs, inheritance hierarchies, and configuration dependenc…
A Deterministic Control Plane for LLM Coding Agents
LLM coding harnesses grant agents broad file and shell access, yet the configuration layer that steers them -- rules files, agent definitions, IDE-specific markdown -- is largely…
NOVA: A Verification-Aware Agent Harness for Architecture Evolution in Industrial Recommender Systems
Industrial advertising recommender models are continuously improved through architecture evolution. Upgrades such as RankMixer, TokenMixer-Large, and MixFormer show that better st…
Mostly Automatic Translation of Language Interpreters from C to Safe Rust
Translating C programs to safe Rust is challenging owing to significant differences in typing constraints, ownership, and borrowing rules. Interpreter programs are particularly im…
The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced Architecture for AI-Assisted Software Development
AI coding agents dramatically accelerate implementation speed but introduce two structural failure modes that existing spec-driven approaches do not fully solve: (1) context explo…
2026-06-25
MedGuards: Multi-Agent System for Reliable Medical Error Detection and Correction
As Large Language Models (LLMs) are increasingly deployed in healthcare settings, accurate error detection and correction in generated or existing text becomes critical, as even m…
Probabilistic Agents in Deterministic Audits: Evaluating Multi-Agent Systems for Automated Audits Based on the German IT-Grundschutz
The NIS-2 Directive mandates robust Risk Management from thousands of small and medium enterprises. To ensure compliance, companies rely on established standards such as the Germa…
Uncertainty Quantification for Computer-Use Agents: A Benchmark across Vision-Language Models and GUI Grounding Datasets
Computer-use agents turn vision-language model (VLM) predictions into executable GUI clicks, so reliable uncertainty estimates are essential for rejection, calibration, miss-sever…
Beyond Function Calling: Benchmarking Tool-Using Agents under Tool-Environment Unreliability
Large language models are increasingly deployed as agents that solve tasks by interacting with external tool environments. Although recent tool-use benchmarks increasingly cover c…
Neglected Free Lunch from Post-training: Progress Advantage for LLM Agents
Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-horizon interactions, irreve…
Explainable Control Framework (XCF) based on Fuzzy Model-Agnostic Explanation and LLM Agent-Supported Interface
Increasing demand for precise and reliable control in complex scenarios has led to the development of increasingly sophisticated controllers, including data-driven approaches empl…
The Unfireable Safety Kernel: Execution-Time AI Alignment for AI Agents and Other Escapable AI Systems
AI agents are granted access to tools, APIs, and other infrastructure, making them active principals in those systems. The dominant approach places controls inside the agent's own…
AI Snitches Get Glitches: Towards Evading Agentic Surveillance
To better assist users with completing challenging tasks, AI agents mediate communications, access data, and interact with different APIs. Many employers (and even nation-states)…
Unlocking Model Potentials Through Adaptive Multi-Agent Scaffolding for Efficient Issue Resolution
Resolving issues with ambiguous and incomplete descriptions, particularly concerning complex bugs, requires a sophisticated, long-horizon workflow. Agents must navigate codebases…
2026-06-24
AGORA: An Archive-Grounded Benchmark for Agentic Workplace Document Reasoning
Large language models are increasingly deployed as agents that reason over documents rather than answer from parametric knowledge. We study archive-grounded reasoning: locating sp…
Are We Ready For An Agent-Native Memory System?
Memory for large language model (LLM) agents has rapidly evolved from simple retrieval-augmented mechanisms into a data management system that supports persistent information stor…
Privacy-Preserving RAG via Multi-Agent Semantic Rewriting: Achieving Confidentiality Without Compromising Contextual Fidelity
Retrieval-Augmented Generation enhances large language models by incorporating external knowledge, but deploying it in sensitive scenarios risks privacy leakage via malicious prom…
Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment
LLM-based dialogue assistants have become mainstream tools for software developers, yet current evaluation benchmarks focus exclusively on functional correctness. This leaves a cr…
Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation
Computer-Use Agents (CUAs) execute high-level user goals by perceiving and acting directly within graphical user interfaces. However, reinforcement learning for CUAs remains diffi…
ReM-MoA: Reasoning Memory Sustains Mixture-of-Agents Scaling
Mixture-of-Agents (MoA) architectures improve inference-time scaling by organizing multiple LLM agents into layered reasoning pipelines. However, existing MoA variants fail to sus…
Qwen-AgentWorld: Language World Models for General Agents
A world model predicts environment dynamics based on current observations and actions, serving as a core cognitive mechanism for reasoning and planning. In this work, we investiga…
Red-Teaming the Agentic Red-Team
The use of agentic systems to perform offensive security operations has moved from a theoretical possibility to a commoditized capability. However, while the community has focused…
Securing LLM-Agent Long-Term Memory Against Poisoning: Non-Malleable, Origin-Bound Authority with Machine-Checked Guarantees
LLM agents increasingly rely on persistent long-term memory, which creates a critical vulnerability that we study here: memory poisoning. An adversary can store untrusted content…
SHERLOC: Structured Diagnostic Localization for Code Repair Agents
LLM agents solve repository-level coding tasks through multi-turn tool use, but utilize half their budget on locating faults before editing. Dedicated localization frameworks have…
NatureBench: Can Coding Agents Match the Published SOTA of Nature-Family Papers?
We introduce NatureBench, a cross-discipline benchmark of 90 tasks distilled from peer-reviewed Nature-family publications, designed to evaluate whether AI coding agents can move…
Bayesian control for coding agents
Modern coding agents pair LLM generators with various tools, including cheap diagnostics and expensive verifiers. The tool-use decisions are typically governed by orchestrators th…
Detecting AI Coding Agents in Open Source: A Validated Multi-Method Census of 180 Million Repositories
Generative AI coding agents are entering the open-source supply chain, yet their diverse and often invisible traces leave their prevalence poorly understood. We introduce a multi-…
LemonHarness Technical Report
As large language model (LLM) agents are applied to longer tasks, they increasingly modify workspace state across multiple rounds of iteration. However, agents typically observe o…
2026-06-23
MAS-PromptBench: When Does Prompt Optimization Improve Multi-Agent LLM Systems?
Multi-agent systems (MAS) offer a scalable path forward for agentic AI, comprising multiple LLM-based agents, each assigned a system prompt and a position within a workflow that g…
EnterpriseClawBench: Benchmarking Agents from Real Workplace Sessions
Enterprise agents increasingly operate inside workspaces: they read heterogeneous files, invoke tools, and deliver business artifacts. We introduce EnterpriseClawBench, an enterpr…
Self-Compacting Language Model Agents
Long agent traces composed of chains of thought and tool calls accumulate stale content that anchor subsequent generations, and eventually outgrow the context window. Existing sca…
Capable but Careless: Do Computer-Use Agents Follow Contextual Integrity?
Computer-use agents (CUAs) now act on a user's behalf across personal applications such as email, calendars, and to-do lists. This cross-application access is useful, but it also…
GIF: Locally Sound Geometric Information Flow Control for LLMs
Large language models increasingly mediate interactions between sensitive data, untrusted inputs, and privileged actions in agentic systems, creating security and privacy risks. T…
Tmax: A simple recipe for terminal agents
Terminal-using agents have quickly become the most popular downstream application of language models (LMs). Despite their prevalence, relatively little academic work has examined…
2026-06-19
LLM agent safety, multi-turn red-teaming, jailbreak benchmarks, adversarial robustness, safety-critical systems
Large language model (LLM) agents are increasingly proposed as supervisory components for safety-critical systems, yet their robustness under sustained, adaptive adversarial press…
Navigating Unreliable Parametric and Contextual Knowledge: Explicit Knowledge Conflict Resolution for LLM Inference
Large language models (LLMs) have achieved strong performance across a wide range of language-based tasks by leveraging both extensive parametric knowledge and in-context learning…
Contagion Networks: Evaluator Bias Propagation in Multi-Agent LLM Systems
When large language models serve as evaluators in multi-agent systems, their systematic evaluation biases propagate through the agent network. We introduce Contagion Networks, a f…
AutoPass: Evidence-Guided LLM Agents for Compiler Performance Tuning
Large Language Models (LLMs) show promise for code compilation tasks, but applying them to runtime performance tuning is difficult due to complex microarchitectural effects and no…
ScholarQuest: A Taxonomy-Guided Benchmark for Agentic Academic Paper Search in Open Literature Environments
Academic paper search is a core step in scientific research, and LLM-based search agents are emerging as a promising paradigm for iterative, intent-driven literature exploration.…
PsyScore: A Psychometrically-Aware Framework for Trait-Adaptive Essay Scoring and ZPD-Scaffolded Feedback
Effective Automated Essay Scoring (AES) are expected to support both reliable assessment and actionable instructional feedback. However, existing approaches often treat scoring an…
LedgerAgent: Structured State for Policy-Adherent Tool-Calling Agents
Policy-adherent tool-calling agents in customer-service domains must maintain task states across turns while calling tools and obeying domain policies. Task states consist of rele…
Analyzing Defensive Misdirection Against Model-Guided Automated Attacks on Agentic AI Systems
Agentic AI systems increasingly rely on language-model components to interpret instructions, process external data, invoke tools, and coordinate with other agents. These capabilit…
RACL: Reasoning-Agent Control Layers for Continuous Metaheuristic Learning
This paper introduces RACL, a Reasoning-Agent Control Layer for metaheuristics. RACL places a reasoning agent above an existing optimizer. The agent does not replace the optimizer…
Beyond Static Endpoints: Tool Programs as an Interface for Flexible Agentic Web Services
In the agentic web era, LLM-based agents increasingly invoke web services as tools, yet most interfaces remain \emph{static endpoints} that poorly express long-horizon workflows w…
Probe-and-Refine Tuning of Repository Guidance for Coding Agents
LLM-based coding agents need higher-level operational knowledge about a repository (which files house which subsystems, how to run the test suite, which workflows have historicall…
Phoenix: Safe GitHub Issue Resolution via Multi-Agent LLMs
We present Phoenix, a multi-agent LLM system that resolves GitHub issues from triage through pull-request creation, combining seven layered safety controls with a baseline-aware t…
N-Version Programming with Coding Agents
This paper revisits the classical concept on N-version programming in the setting of contemporary AI coding agents. Revisiting the seminal Knight-Leveson experiment, we study whet…
2026-06-18
Enhancing Decision-Making with Large Language Models through Multi-Agent Fictitious Play
Large language model (LLM)-based multi-agent systems (MAS) have demonstrated great potential in solving tasks with execution complexity, by distributing subtasks across cooperativ…
A Technical Taxonomy of LLM Agent Communication Protocols
As large language models (LLMs) advance and multi-agent systems aim to overcome the limits of standalone agents, robust communication protocols are becoming essential infrastructu…
CAPRA: Scaling Feedback on Software Architecture Deliverables with a Multi-Agent LLM System
Automated assessment in software engineering education has advanced significantly for code grading and essay scoring. However, reviewing software architecture deliverables, which…
AdsMind: A Physics-Grounded Multi-Agent System for Self-Correcting Discovery of Adsorption Configurations on Heterogeneous Catalyst Surfaces
Identifying the lowest-energy surface-adsorbate configuration is critical for modeling heterogeneous catalysis, yet exhaustive exploration with ab initio calculations is computati…
CodeSentinel: A Three-Layer Defense Against Indirect Prompt Injection in Code Contexts
Code large language models increasingly retrieve external code context from repositories, documentation, issue threads, and coding-agent environments, creating an indirect prompt-…
Data Intelligence Agents: Interpreting, Modeling, and Querying Enterprise Data via Autonomous Coding Agents
Production data integration is bottlenecked by repeated, lossy handoffs between data owners, engineers, and analysts who must collaboratively discover, structure, and query enterp…
2026-06-17
WEQA: Wearable hEalth Question Answering with Query-Adaptive Agentic Reasoning
Language models are remarkably capable at medical question answering, in some cases surpassing the accuracy of general physicians. However, answering questions about wearable heal…
LLM Consumer Behavior Theory: Foundations of a Novel Research Field
Large language models (LLMs) are increasingly deployed as autonomous agents that make consumption decisions on behalf of users. This shift raises fundamental questions for consume…
RubricsTree: Scalable and Evolving Open-Ended Evaluation of Personal Health Agents across Health Memory and Medical Skills
The LLM-empowered personal health agents with user health (sensor) metrics have offered a promising pathway to alleviate global disparities in healthcare access. However, large-sc…
Your AI Travel Agent Would Book You a Bullfight: An Agentic Benchmark for Implicit Animal Welfare in Frontier AI Models
AI agents are moving from advisors to actors, booking travel, planning menus, and running procurement on behalf of users. Existing benchmarks for AI and animal welfare evaluate mo…
Compositional Skill Routing for LLM Agents: Decompose, Retrieve, and Compose
LLM agents increasingly rely on external skills -- reusable tool specifications -- but real-world tasks often require composing multiple skills, not just selecting one. We formali…
ProvenanceGuard: Source-Aware Factuality Verification for MCP-Based LLM Agents
Tool-using LLM agents increasingly use the Model Context Protocol (MCP) to answer from heterogeneous evidence sources, including search, APIs, databases, clinical records, and for…
Trustworthy Self-Composable Big-Data-as-a-Service: An LLM-Orchestrated Multi-Agent Framework for Automated Data Engineering, AutoML, MLOps Deployment, and Drift-Aware Lifecycle Optimization
Big-Data-as-a-Service (BDaaS) platforms require re liable automation across data ingestion, cleaning, feature engi neering, model development, deployment, and post-deployment moni…
Seeing Is Not Screening: Multimodal Hidden Instruction Attacks on Agent Skill Scanners
Agent skills are emerging as an important attack surface in LLM-based systems. Through an empirical study of existing skill scanners, we find that current defenses primarily rely…
A Red-Team Study of Anthropic Fable 5 & Opus 4.8 Models
We evaluate the adversarial robustness of two frontier large language models (LLMs) developed by Anthropic, Fable 5 and Opus 4.8, against four families of automated jailbreak atta…
PreAct: Computer-Using Agents that Get Faster on Repeated Tasks
Computer-using agents drive real software through the screen -- clicking and typing -- but they solve every task from scratch: asked to repeat a task, an agent re-reads the screen…
All Smoke, No Alarm: Oracle Signals in Agent-Authored Test Code
Software practitioners increasingly use AI coding agents that generate test code alongside production code in open source pull requests (PRs). Recent studies report more than 932,…
LoopCoder-v2: Only Loop Once for Efficient Test-Time Computation Scaling
Looped Transformers scale latent computation by repeatedly applying shared blocks, but sequential looping increases latency and KV-cache memory with the loop count. Parallel loop…
GameCraft-Bench: Can Agents Build Playable Games End-to-End in a Real Game Engine?
Game generation is an emerging application of coding agents, requiring models to transform natural-language specifications into playable interactive systems. Unlike traditional co…
Position: Coding Benchmarks Are Misaligned with Agentic Software Engineering
Coding agents have become a major mode of software engineering, but the benchmarks we use to compare them were designed in a pre-agent era: they collapse model, harness, and envir…
2026-06-16
OpenClaw-Skill: Collective Skill Tree Search for Agentic Large Language Models
Equipping Large Language Model (LLM) agents with effective skills is crucial for solving complex tasks in real-world systems like OpenClaw. In this work, we aim to develop a frame…
Context-Aware RL for Agentic and Multimodal LLMs
Large language models (LLMs) often fail when answering requires identifying a small but decisive piece of evidence within a long or complex context, such as a single line in a too…
Benchmarking LLM Agents on Meta-Analysis Articles from Nature Portfolio
Meta-analysis is a demanding form of evidence synthesis that combines literature retrieval, PI/ECO-guided study selection, and statistical aggregation. Its structured, verifiable…
Consensus-based Agentic Large Language Model Framework for Harmonized Tariff Schedule Code Classification
Accurate Harmonized Tariff Schedule (HTS) code classification is essential for customs clearance, duty assessment, trade statistics, and regulatory compliance in maritime logistic…
How Much Can We Trust LLM Search Agents? Measuring Endorsement Vulnerability to Web Content Manipulation
Large language model (LLM)-based search agents synthesize open-web content into actionable recommendations on behalf of users, creating a risk that attacker-published pages are tr…
LabOSBench: Benchmarking Computer Use Agents for Scientific Instrument Control
Current computer-use benchmarks primarily focus on software operation tasks in virtualized systems, whereas scientific instrumentation scenarios require coordinated control over c…
DEEPRUBRIC: Evidence-Tree Rubric Supervision for Efficient Reinforcement Learning of Deep Research Agents
Deep research agents synthesize long-form reports by searching and reasoning over retrieved evidence. Reinforcement learning with rubric-based rewards improves these agents by opt…
Binary Tracking for Spatial QA and Navigation with Open Vision-Language Models
This work addresses spatial question answering for service robots traversing long egocentric routes. Given a query such as "where can I find a dry cleaner on the way back home?",…
MyPCBench: A Benchmark for Personally Intelligent Computer-Use Agents
Current benchmarks for computer-use agents evaluate models in impersonal environments. This leaves a gap between evaluation and deployment where personal assistants are expected t…
Agent trajectories as programs: fingerprinting and programming coding-agent behavior
Benchmark scores tell you what an agent got right; they do not tell you how it got there. In this work, we introduce methods for comparing agents procedurally in different context…
Towards LLM Accelerated Rapid Reviews for Software Tool Discovery -- Case for Log Anomaly Detection
In software engineering research, the primary outcome is frequently a tool. However, for practitioners and academics alike, it is hard to tell which tools are maintained and do th…
2026-06-12
EvoArena: Tracking Memory Evolution for Robust LLM Agents in Dynamic Environments
Large language model (LLM) agents have achieved strong performance on a wide range of benchmarks, yet most evaluations assume static environments. In contrast, real-world deployme…
Who Pays the Price? Stakeholder-Centric Prompt Injection Benchmarking for Real-world Web Agents
Web agents driven by large language models (LLMs) are increasingly deployed in real-world environments, where they operate over untrusted web content and execute actions with dire…
An LLM System for Autonomous Variational Quantum Circuit Design
The design of high performing quantum circuits remains largely dependent on human expertise. We introduce an autonomous agentic framework that employs large language models (LLMs)…
SpatialClaw: Rethinking Action Interface for Agentic Spatial Reasoning
Spatial reasoning, the ability to determine where objects are, how they relate, and how they move in 3D, remains a fundamental challenge for vision-language models (VLMs). Tool-au…
ArogyaSutra: A Multi-Agent Framework for Multimodal Medical Reasoning in Indic Languages
Multimodal Large Language Models (MLLMs) have shown promising reasoning capabilities in general domains, yet their performance remains limited in specialized settings such as heal…
Why Sampling Is Not Choosing: Intentionality, Agency, and Moral Responsibility in Large Language Models
Recent advances in large language models (LLMs) have prompted claims that such systems exhibit agency or qualify as moral agents. This paper argues that these attributions are mis…
Reward Modeling for Multi-Agent Orchestration
Multi-Agent Systems (MAS) built on Large Language Models (LLMs) require effective orchestration to coordinate specialized agents, yet training such orchestrators is hindered by li…
From Passive Generation to Investigation: A Proactive Scientific Peer Review Agent
Large language models (LLMs) have shown promise in automating scientific peer review. However, existing approaches often struggle to generate in-depth reviews supported by concret…
AgentBeats: Agentifying Agent Assessment for Openness, Standardization, and Reproducibility
Agent systems are advancing quickly across domains, but their evaluation remains fragmented. Most benchmarks rely on fixed, LLM-centric harnesses that require heavy integration, c…
SkillCAT: Contrastive Assessment and Topology-Aware Skill Self-Evolution for LLM Agents
Skill self-evolution methods for LLM agents aim to turn execution trajectories into reusable skill documents, but current pipelines typically learn from one trajectory per task, m…
Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research Agenda
LLM-based agents are entering regulated industries where they automate judgment intensive quality management processes. We argue that symbolic structures already embedded in these…
ComAct: Reframing Professional Software Manipulation via COM-as-Action Paradigm
Existing computer-use agents remain fundamentally limited in professional software manipulation: GUI-based agents suffer from fragile visual grounding and long-horizon error accum…
Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents
Interactive LLM agents are becoming part of daily work, but they do not reliably become easier to work with over time: a correction remembered in one session may still be violated…
Nous: An Attempt to Extract and Inject the Cognition Behind Prediction-Market Behavior
As LLM agents proliferate in prediction markets and collective decision-making, they risk a cognitive monoculture: agents built on shared foundation models produce correlated fore…
Understanding the Rejection of Fixes Generated by Agentic Pull Requests -- Insights from the AIDev Dataset
AI coding agents are increasingly used to generate pull requests (PRs) that propose code fixes in software projects. From a first exploration of the AIDev dataset, we find that 46…
Recursive Agent Harnesses
Recursive language models (RLMs) showed that recursion over model calls is an effective strategy for long-context reasoning, and production coding agents have begun to write code…
2026-06-11
Measuring Epistemic Resilience of LLMs Under Misleading Medical Context
Large language models (LLMs) now reach expert-level scores on medical licensing exams, encouraging the assumption that high scores imply safe medical judgment while patients incre…
A Lightweight Multi-Agent Framework for Automated Concrete Barrier Design
The design of reinforced concrete highway barriers is a safety-critical process that requires strict compliance with regulatory provisions such as the AASHTO-LRFD bridge design gu…
Claw-SWE-Bench: A Benchmark for Evaluating OpenClaw-style Agent Harnesses on Coding Tasks
General-purpose agents such as OpenClaw are increasingly used as autonomous tool users, but their coding ability is difficult to measure under SWE-bench: a generic agent does not…
Which Models Are Our Models Built On? Auditing Invisible Dependencies in Modern LLMs
Modern LLM training pipelines increasingly rely on other models to generate data, filter corpora, judge outputs, and guide development decisions. These dependencies are recursive:…
APPO: Agentic Procedural Policy Optimization
Recent advances in agentic Reinforcement Learning (RL) have substantially improved the multi-turn tool-use capabilities of large language model agents. However, most existing meth…
Fourier Features Let Agents Learn High Precision Policies with Imitation Learning
High-precision robotic manipulation requires fine-grained spatial reasoning that is often difficult to achieve with RGB-only policies due to depth ambiguity and perspective scale…
OCELOT: Inference-Leakage Budgets for Privacy-Preserving LLM Agents
Large language model (LLM) agents increasingly act on a user's behalf -- reading personal files, calling tools, transacting with external services -- possibly leaking personally i…
PROJECTMEM: A Local-First, Event-Sourced Memory and Judgment Layer for AI Coding Agents
AI coding assistants now support a growing share of software work, from quick scripts to production applications. Yet these agents remain largely stateless: each new session re-re…
Exploration Structure in LLM Agents for Multi-File Change Localization
Software engineering tools increasingly rely on LLM based agents to localize files to change to resolve a software issue. Most AI agents explore repositories linearly, that is, vi…
Agents All the Way Down; A Methodology for Building Custom AI Agents from Substrate to Production
Custom AI agents areagents that live inside their own application, talk to their own data and tools, enforce their own security boundaries, and carry their own brand and audit tra…
2026-06-10
T1-Bench: Benchmarking Multi-Scenario Agents in Real-World Domains
Recent advances in reasoning and tool-calling capabilities of large language models (LLMs) have enabled increasingly capable agentic systems. However, existing benchmarks remain l…
Role-Agent: Bootstrapping LLM Agents via Dual-Role Evolution
Although Large Language Model (LLM) agents have demonstrated strong performance on complex tasks, their learning is often limited by inefficient interaction feedback and static tr…
ABC-Bench: An Agentic Bio-Capabilities Benchmark for Biosecurity
Large language models (LLMs) are rapidly acquiring capabilities relevant to biological research, from literature synthesis to interpretation of experimental data. Increasingly, LL…
Mind the Gap: Can Frontier LLMs Pass a Standardized Office Proficiency Exam?
The deployment of Large Language Model (LLM) agents for computer automation is accelerating, yet their ability to navigate complex, professional-grade productivity software is lar…
The Shibboleth Effect: Auditing the Cross-Lingual Distributional Skew of Large Language Models
This study investigates cross-lingual distributional skew (the Shibboleth Effect) in frontier large language models (LLMs) subjected to sustained adversarial conditions. We develo…
TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning
Reinforcement learning with verifiable rewards (RLVR) is a promising approach for enhancing reasoning and agentic behavior in large language models. However, rollout-intensive pol…
VISTA: A Versatile Interactive User Simulation Toolkit for Agent Evaluation
Evaluation remains a critical bottleneck for interactive agent development. Existing evaluation methods often rely on static benchmarks, which fail to capture the dynamic, multi-s…
Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activation
Large language models (LLMs) rely on tool use to act as autonomous agents, yet often fail in multi-step execution due to insufficient tool-related knowledge and ineffective knowle…
Toward Secure LLM Agents: Threat Surfaces, Attacks, Defenses, and Evaluation
Large language model (LLM) agents are rapidly moving from conversational interfaces to software components that plan, invoke tools, maintain memory, and act on external environmen…
Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields
Recent years have witnessed the rapid evolution of AI agents toward handling increasingly complex, real-world tasks. However, existing benchmarks rarely evaluate whether agents ca…
Data Journalist Agent: Transforming Data into Verifiable Multimodal Stories
Data tells stories that shape society; the data journalist's job is to turn raw information into stories non-experts can trust. A high-quality news feature takes a newsroom team w…
Frontier Coding Agents Use Metaprogramming to Adapt to Unfamiliar Programming Languages
LLM-based coding agents are usually evaluated in familiar software settings: mainstream languages, common libraries, and public repositories. These benchmarks remain important, bu…
AutoPDE: Reliable Agentic PDE Solving via Explicitly Represented Solver Strategies
Numerical solvers for partial differential equations (PDEs) are core computational tools in science and engineering. Building reliable PDE solvers requires not only executable cod…
DeNovoSWE: Scaling Long-Horizon Environments for Generating Entire Repositories from Scratch
As the capabilities of LLM-based code agents continue to advance, their expected role is expanding beyond localized bug fixing in existing codebases toward architecting and implem…
2026-06-09
SpatialWorld: Benchmarking Interactive Spatial Reasoning of Multimodal Agents in Real-World Tasks
Spatial reasoning is a foundational capability for multimodal large language models (MLLMs) to perceive and operate within the physical world. However, existing benchmarks predomi…
IS-CoT: Breaking the Long-form Generation Collapse via Interleaved Structural Thinking
Generating coherent and controllable long-form content remains a persistent challenge for Large Language Models (LLMs). While reasoning-enhanced models have demonstrated success i…
OmniGameArena: A Unified UE5 Benchmark for VLM Game Agents with Improvement Dynamics
Vision-language model (VLM) agents are increasingly deployed in interactive game environments. Yet game benchmarks for VLM agents typically report a single first-attempt score per…
SearchSwarm: Towards Delegation Intelligence in Agentic LLMs for Long-Horizon Deep Research
Large language models are increasingly expected to handle complex, long-horizon real-world tasks whose context demands can grow without bound, yet model context windows remain inh…
Civil Court Simulation with Large Language Models
Court simulation bridges legal education and judicial practice, yet human-based simulations are costly and difficult to scale. Large language models (LLMs) offer a scalable altern…
SecureClaw: Clawing Back Control of LLM Agents
Tool-using large language model (LLM) agents face two distinct security failures: unauthorized external actions and exposure of sensitive plaintext inside the runtime before any f…
AI Scientists Are Only as Good as Their Evidence: A Stratified Ablation of Proprietary Data and Reasoning Skills in Drug-Asset Valuation
AI Scientist agents are often evaluated as if capability were mainly a function of model quality, prompting, or reasoning scaffolds. We test a different hypothesis in drug-asset v…
WeaveBench: A Long-Horizon, Real-World Benchmark for Computer-Use Agents with Hybrid Interfaces
Computer-use agents (CUAs) increasingly operate in runtimes that combine visual desktop control, command-line execution, code editing, browsers, and external tools. Existing bench…
Brain-Prompt Injection: A Route-Safety Audit for BCI-LLM Agents
BCI-to-agent pipelines turn decoded neural activity into an authorization channel for tool-use agents, exposing a new attack surface we call \emph{brain-prompt injection}: signal-…
PRISM: Recovering Instruction Sets from Language Model Activations
As LLMs are deployed as agents, reliable monitoring requires knowing not only what they output, but which instructions are steering their behavior. This is difficult when models i…
SIGA: Self-Evolving Coding-Agent Adapters for Scientific Simulation
Advanced scientific simulators expose specialized input languages that turn simulation goals into executable configurations, but learning them can cost domain scientists hours to…
From 0-to-1 to 1-to-N: Reproducible Engineering Evidence for MetaAI Recursive Self-Design
Recursive self-design refers to AI-assisted modification of the mechanisms by which an AI system is built, evaluated, and improved. This paper treats MetaAI not as a mature paradi…
Self-Harness: Harnesses That Improve Themselves
The performance of LLM-based agents is jointly shaped by their base models and the harnesses that mediate their interaction with the environment. Because different models exhibit…
2026-06-05
CollabSim: A CSCW-Grounded Methodology for Investigating Collaborative Competence of LLM Agents through Controlled Multi-Agent Experiments
Multi-agent systems (MAS) built on large language models have shown growing promise, with their effectiveness resting on agents' ability to coordinate through text-based channels…
AdaPlanBench: Evaluating Adaptive Planning in Large Language Model Agents under World and User Constraints
Planning for real-world problems by language models often involves both world and user constraints, which may not be fully specified upfront and are progressively disclosed throug…
Beyond tokens: a unified framework for latent communication in LLM-based multi-agent systems
Multi-agent systems built on large language models (LLMs) have become a prevailing paradigm for tackling complex reasoning, planning, and tool-use tasks. The dominant communicatio…
CollabBench: Benchmarking and Unleashing Collaborative Ability of LLMs with Diverse Players via Proactive Engagement
While LLM-based agents excel at individual tasks, effective collaboration with realistic human partners remains challenging. Most of the existing conversation-level collaborative…
PlanBench-V: A Spatial Planning Map Benchmark for Vision-Language Models
Spatial planning maps are central to territorial governance, translating planning objectives, regulations, and spatial strategies into visual forms for decision-making, public com…
EGTR-Review: Efficient Evidence-Grounded Scientific Peer Review Generation via Multi-Agent Teacher Distillation
Scientific peer review generation has attracted increasing attention for reducing reviewing burdens and providing timely feedback. However, existing Large Language Model (LLM)-bas…
Reducing Hallucinations in Complex Question Answering using Simple Graph-based Retrieval-Augmented Generation (long version)
Large language models (LLMs) have fundamentally transformed the landscape of Natural Language Processing. Despite these advances, LLMs and LLM-based systems remain prone to a vari…
From Risk Classification to Action Plan Remediation: A Guardrail Feedback Driven Framework for LLM Agents
LLM-based guardrails typically safeguard agents by evaluating proposed actions or inputs before execution, producing safety signals such as binary allow/deny decisions, risk categ…
Beyond Similarity: Trustworthy Memory Search for Personal AI Agents
Personal AI agents increasingly rely on long-term memory to provide persistent personalization across sessions. However, existing memory pipelines are largely driven by semantic s…
ADK Arena: Evaluating Agent Development Kits via LLM-as-a-Developer
The rapid proliferation of Agent Development Kits (ADKs), SDK-level frameworks for building LLM-powered autonomous agents, has outpaced any empirical understanding of how framewor…
Asuka-Bench: Benchmarking Code Agents on Underspecified User Intent and Multi-Round Refinement
Existing code-generation benchmarks score a single mapping from a complete prompt to a one-shot output. However, real web development is different. Users seldom write a full spec…
SmellBench: Towards Fine-Grained Evaluation of Code Agents on Refactoring Tasks
Code Agents have achieved remarkable advances in recent years, exhibiting strong capabilities across a wide range of software engineering tasks. However, their misuse often produc…
From Failed Trajectories to Reliable LLM Agents: Diagnosing and Repairing Harness Flaws
LLM-based agents increasingly rely on harnesses that provide execution environments, tool interfaces, context, lifecycle orchestration, observability, verification, and governance…
RAT: RunAnyThing via Fully Automated Environment Configuration
Automating repository-level software engineering tasks is a foundational challenge for autonomous code agents, largely due to the difficulty of configuring executable environments…
Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?
AI coding agents are increasingly embedded in real-world software development, collaborating with human developers while gaining broader access to codebases and tools. This create…
Converted, Not Equivalent: Benchmarking Codebase Conversion via Observational Equivalence
Coding agents increasingly act as codebase-scale collaborators that can assist with codebase conversion, but this progress has exposed a critical weakness: agents often over-trust…
2026-06-04
Evaluating Large Language Models in Dynamic Clinical Decision-Making with Standardized Patient Cases
Large language models (LLMs) are increasingly proposed as clinical agents, yet static, single-turn benchmarks cannot capture how a model dynamically delivers care across an encoun…
Self-Evolving Deep Research via Joint Generation and Evaluation
Large Language Models (LLMs) have become increasingly adopted in daily applications, with deep research standing out as a particularly important capability. Unlike traditional que…
Agent Planning Benchmark: A Diagnostic Framework for Planning Capabilities in LLM Agents
Planning is central to LLM agents: before acting, an agent must decompose goals, select tools, reason over constraints, and decide when a task is infeasible. Yet existing agent ev…
SMADE-IE: Sparse Multi-Agent Framework with Evidence-Driven Debate for Zero-Shot Information Extraction
Zero-shot information extraction (IE) with large language models (LLMs) has attracted increasing attention due to its flexibility in adapting to new schemas and domains without ta…
Deliberate Evolution: Agentic Reasoning for Sample-Efficient Symbolic Regression with LLMs
Symbolic regression (SR) discovers compact mathematical expressions from data, yet recent LLM-based evolutionary methods remain sample-inefficient because they rely mainly on scal…
Exploring the Topology and Memory of Consensus: How LLM Agents Agree, Fragment, or Settle When Forming Conventions
How much should an LLM agent remember, and how should multi-agent systems be connected when trying to reach consensus? We show these two design choices interact in a way that flip…
What If Prompt Injection Never Left? Exploring Cross-Session Stored Prompt Injection in Agentic Systems
Modern agentic systems transform LLMs from session-bounded assistants into stateful systems that persist and evolve shared world state across sessions through memories, filesystem…
Caught in the Act(ivation): Toward Pre-Output and Multi-Turn Detection of Credential Exfiltration by LLM Agents
LLM agents often place sensitive credentials in the same context window as untrusted retrieved content, creating a direct path for indirect prompt injection to induce credential e…
AgentJet: A Flexible Swarm Training Framework for Agentic Reinforcement Learning
We present AgentJet, a distributed swarm training framework for large language model (LLM) agent reinforcement learning. Unlike centralized frameworks that tightly couple agent ro…
From Untrusted Input to Trusted Memory: A Systematic Study of Memory Poisoning Attacks in LLM Agents
Memory is a core component of AI agents, enabling them to accumulate knowledge across interactions and improve performance. However, persistent memory introduces the risk of memor…
Toward Pre-Deployment Assurance for Enterprise AI Agents: Ontology-Grounded Simulation and Trust Certification
Pre-deployment verification of enterprise artificial intelligence (AI) agents remains a critical gap between large language model (LLM) capability benchmarking and production depl…
Can Generalist Agents Automate Data Curation?
Curating training data is among the most consequential yet labor-intensive parts of modern AI development: practitioners iteratively propose, implement, evaluate, and revise data…
The Meta-Agent Challenge: Are Current Agents Capable of Autonomous Agent Development?
Current AI benchmarks evaluate agents on task execution within human-designed workflows. These evaluations fundamentally fail to measure a critical next-level capability: whether…
The Saturation Trap and the Subjectivity of Intervention Timing: Why Affect-Based Triggers and LLM Judges Fail to Time Interventions on Autonomous Agents
As autonomous AI agents move from conversational systems to long-horizon software execution, runtime safety layers that decide when to interrupt an agent have become essential. We…
Trustworthy AI Software Engineers
With the rapid rise of AI coding agents, the fundamental premise of what it means to be a software engineer is in question. In this vision paper, we examine what it means for an A…
2026-06-03
Agentic Chain-of-Thought Steering for Efficient and Controllable LLM Reasoning
Large language models improve final-answer accuracy through extended chain-of-thought reasoning, but often spend tokens inefficiently and offer little inference-time control. Exis…
A Training-Free Mixture-of-Agents Framework for Multi-Document Summarization using LLMs and Knowledge Graphs
Multi-Document Summarization (MDS) plays a critical role in distilling essential information from collections of textual data. Existing approaches often struggle to capture comple…
Adaptive Latent Agentic Reasoning
Large reasoning models improve performance by generating extended chain-of-thought (CoT) reasoning, but this behavior becomes inefficient when applied to LLM agents. Current LLM a…
MedCUA-Bench: A Screenshot-Only Benchmark for Clinical Computer-Use Agents
Computer-use agents could automate repetitive screen-based clinical work, but their reliability in medical graphical user interfaces remains largely unvalidated. Existing benchmar…
From Control Boundary to Insurance Claim: Reconstructing AI-Mediated Losses Through the CER Framework
AI losses that arise through an insured organization's generative or agentic AI system require state reconstruction, not merely event reconstruction, because the relevant state ch…
Acceptance-Test-Driven Evaluation Protocols for Business-Centric LLM Systems
Large language model (LLM) applications are increasingly expected to satisfy deterministic institutional requirements while relying on probabilistic generative components. This mi…
Toward a Modular Architecture for Embedded AI Agent Systems at the Edge
The rise of Large Language Models (LLMs) has enabled agentic AI capable of complex reasoning and tool use; however, deploying such autonomy in pervasive computing environments rem…
Which Defense Closes Which Threat? Attributing OWASP-LLM-Top-10 Coverage and Its Brittleness Under Paraphrasing
Production LLM applications stack several defense families -- refusal-phrase filters, token-budget controls, model allowlists, rate limits, tool-registry authentication -- yet exi…
What Makes Interaction Trajectories Effective for Training Terminal Agents?
Stronger code agents are commonly assumed to be superior teachers for post-training, yet this assumption remains poorly disentangled from task difficulty, harness design, and stud…
Cross-Lingual Token Arbitrage: Optimizing Code Agent Context Windows via Local LLM Preprocessing
AI-assisted coding agents are bottlenecked by input-token cost. Two pathologies of raw human input drive much of this overhead: tokenization inefficiency for non-English text and…
Handoff Debt: The Rediscovery Cost When Coding Agents Take Over Interrupted Tasks
Coding-agent benchmarks evaluate whether a single uninterrupted agent can resolve a repository issue. Real software work is messier: tasks are interrupted, reassigned, reviewed, a…
VulnAgent-R2: Evidence-Calibrated Multi-Agent Auditing for Repository-Level Vulnerability Detection
Software vulnerabilities often depend on cross-file data flow, build options, framework conventions, and runtime guards, so isolated function classifiers produce fragile and poorl…
AgentLens: Revealing The Lucky Pass Problem in SWE-Agent Evaluation
Evaluation of software engineering (SWE) agents is dominated by a binary signal: whether the final patch passes the tests. This outcome-only view treats a principled solution and…
EvoTrainer: Co-Evolving LLM Policies and Training Harnesses for Autonomous Agentic Reinforcement Learning
Autonomous LLM training is often framed as recipe search, which leaves the training harness largely static. This limitation sharpens in agentic RL, where shifting bottlenecks and…
Human-AI Collaboration and the Transformation of Software Engineering Work
The integration of Generative AI (GenAI) and Agentic AI into software development is reconfiguring software engineering from an activity centered on human authorship of code into…
2026-06-02
POIROT: Interrogating Agents for Failure Detection in Multi-Agent Systems
Orchestrating Large Language Models into Multi-Agent Systems (LLM-MAS) has unlocked remarkable reasoning capabilities, yet emergent failures and hallucinations that resist charact…
MCP-Persona: Benchmarking LLM Agents on Real-World Personal Applications via Environment Simulation
The Model Context Protocol (MCP) has emerged as a transformative standard for connecting large language models (LLMs) with external data sources and tools, and has been rapidly ad…
AgentPLM: Agentic Protein Language Models with Reasoning-Augmented Decoding for Protein Sequence Design
Protein language models (PLMs) are passive oracles: they generate sequences in a single forward pass with no mechanism to consult external biophysical feedback or redirect generat…
Auditing Asset-Specific Preferences in Financial Large Language Models: Evidence from Bitcoin Representations and Portfolio Allocation
Large language models now power robo-advisors and trading agents, yet whether they carry built-in biases toward specific assets is largely untested. We ask three questions: do LLM…
K-BrowseComp: A Web Browsing Agent Benchmark Grounded in Korean Contexts
Frontier model evaluations are shifting from foundational capabilities (e.g., instruction following and reasoning) toward compositional, agentic ones, but Korean agentic benchmark…
AGENTCL: Toward Rigorous Evaluation of Continual Learning in Language Agents
Language agents spend substantial inference time solving individual tasks, yet the experience acquired in one episode is often underutilized in future episodes. Continual learning…
MOC: Multi-Order Communication in LLM-based Multi-Agent Systems
Despite the remarkable progress of Large Language Model (LLM) based Multi-Agent Systems, most research focuses on optimizing coordination topology while largely underexploring the…
Unified Context Evolution for LLM Agents
LLM-based agents can solve multi-step interactive tasks by combining reasoning with environment feedback, yet each episode starts from the same fixed context and any useful strate…
AgentRedBench: Dynamic Redteaming and Integration-Aware Defense for LLM Agents over SaaS Integrations
Indirect prompt injection in tool-use agents is a concrete production threat: LLM agents read from integrations (third-party services such as Gmail, Salesforce, or Jira accessed t…
SafeMCP: Proactive Power Regulation for LLM Agent Defense via Environment-Grounded Look-Ahead Reasoning
As Large Language Model (LLM) agents increasingly leverage the Model Context Protocol (MCP) to operate in complex environments, the expansion of their action spaces offers agents…
SeClaw: Spec-Driven Security Task Synthesis for Evaluating Autonomous Agents
Autonomous LLM agents increasingly operate in stateful environments where they access tools, files, memory, and external services. While such capabilities enable complex real-worl…
SkillHarm: Lifecycle-Aware Skill-Based Attacks via Automated Construction
Agent skills occupy a privileged position in the agent workflow, as agents are expected to implicitly follow and execute them, rendering third-party skills a vulnerable attack sur…
2026-05-29
KVoiceBench, KOpenAudioBench, and KMMAU: Agent-Driven Korean Speech Benchmarks for Evaluating SpeechLMs
Speech language models (SpeechLMs) have achieved substantial progress by extending large language models (LLMs) to the speech modality. However, SpeechLM evaluation remains heavil…
LegalGraphRAG: Multi-Agent Graph Retrieval-Augmented Generation for Reliable Legal Reasoning
Graph-based Retrieval-Augmented Generation (GraphRAG) advances flat document retrieval by structuring knowledge as relational graphs, enabling more coherent and effective reasonin…
DisasterBench: Benchmarking LLM Planning under Typed Tool Interface Constraints
Disasters cause severe societal impacts, demanding rapid coordination of heterogeneous AI tools, from satellite analysis to flood prediction and damage assessment, into coherent m…
LCO: LLM-based Constraint Optimization for Safer Agentic LLMs in Real-world Tasks
Large Language Models (LLMs) are increasingly acting as autonomous agents, but their continuous interaction with the environment can lead to in-context reward hacking (ICRH), a ph…
Provably Secure Agent Guardrail
As large language models transition from bounded generative engines to agents with expansive execution privileges, AI going out of control precipitates a fundamental crisis in art…
AgentDoG 1.5: A Lightweight and Scalable Alignment Framework for AI Agent Safety and Security
Modern open-world agents such as OpenClaw exhibit powerful cross-environment execution capabilities yet introduce broad new safety risk sources. Meanwhile, advanced frontier AI mo…
Physics Is All You Need? A Case Study in Physicist-Supervised AI Development of Scientific Software
Are AI agents tools, co-authors, or researchers? We present a quantified case study ($N=1$): a physicist supervising an AI coding agent (Claude Code, Sonnet and Opus models) over…
Discovering Cooperative Pipelines: Autoresearch for Sequential Social Dilemmas
We study two-level autoresearch for cooperation: an outer-loop AI agent autonomously redesigns the inner-loop pipeline of an LLM policy-synthesis system for multi-agent Sequential…
2026-05-28
TRACER: Turn-level Regret Matching with Inner Reinforcement Credit for Cooperative Multi-LLM Reasoning
Large language models increasingly rely on either reinforcement learning or multi-agent prompting to improve reasoning, yet these two paradigms remain difficult to combine. Direct…
Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents
Recent advancements in multimodal large language models (MLLMs) have shown exceptional potential in enabling mobile-using agents to autonomously execute human instructions. Howeve…
Agent Explorative Policy Optimization for Multimodal Agentic Reasoning
Vision-language models with extended reasoning succeed on complex problems, but many real-world problems require external tools that internal reasoning alone often cannot resolve.…
VeriTrip: A Verifiable Benchmark for Travel Planning Agents over Unstructured Web Corpora
Existing benchmarks have laid the foundation for travel planning agents by establishing API-centric paradigms. However, as the capabilities of Autonomous Agents continue to advanc…
Do Agents Need Semantic Metadata? A Comparative Study in Agentic Data Retrieval
In the era of autonomous agents, machine-actionable data is critical for data-driven workflows. For more than a decade, semantic metadata like schema.org has anchored the FAIR pri…
Evaluating the Realism of LLM-powered Social Agents: A Case Study of Reactions to Spanish Online News
LLM-powered social agents are increasingly used to simulate online social behavior, yet their realism remains difficult to validate. Existing work has largely relied on general-pu…
Self-Improving Language Models with Bidirectional Evolutionary Search
Search has been proposed as an effective method for self-improving language models and agentic systems, both for post-training sample generation and for inference. However, widely…
Learn from Weaknesses: Automated Domain Specialization for Small Computer-Use Agents
Computer-use agents (CUAs) have recently made substantial progress, but deploying a separate large expert for each software domain remains expensive. Small open computer-use agent…
LACUNA: Safe Agents as Recursive Program Holes
LLM agents increasingly act by writing code, yet a split persists between the runtime that drives the agent and the code the model writes. The runtime owns the loop, context, and…
Technical Report: Exploring the Emerging Threats of the Agent Skill Ecosystem
We analyzed 3,984 AI agent skills from major marketplaces and found 76 confirmed malicious payloads, including credential theft, backdoor installation, and data exfiltration. 13.4…
Calibrating Conservatism for Scalable Oversight
Agentic AI systems capable of autonomous planning and extended environmental interaction pose a fundamental control problem: how can humans maintain meaningful oversight of system…
2026-05-27
Traceable Knowledge Graph Reasoning Enables LLM-Assisted Decision Support for Industrial VOCs in the Steel Industry
Key knowledge for steel-industry volatile organic compounds (VOCs) governance is scattered across unstructured scientific literature, making it difficult to integrate process, pol…
Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation
Vision-Language Models (VLMs) have shown rapid progress in mobile GUI navigation. This paper presents a systematic study of data scaling, benchmarking, and reasoning for VLM-based…
Learning to Act under Noise: Enhancing Agent Robustness via Noisy Environments
Recent advances in large language models (LLMs) have facilitated the widespread deployment of LLMs as interactive agents capable of reasoning, planning, and tool use. Despite stro…
VitaBench 2.0: Evaluating Personalized and Proactive Agents in Long-Term User Interactions
Large language models (LLMs) have evolved into interactive agents that collaborate with users in real-world tasks. Effective collaboration in such settings increasingly depends on…
MUSE-Autoskill: Self-Evolving Agents via Skill Creation, Memory, Management, and Evaluation
Large language model (LLM) agents rely on reusable skills to solve complex tasks. However, existing skill creation approaches treat skills as isolated and static artifacts, limiti…
QUACK: Questioning, Understanding, and Auditing Communicated Knowledge in Multimodal Social Deduction Agents
Social deduction games have become a popular testbed for probing reasoning, deception, coordination, and belief modeling in Large Language Model (LLM) agents. However, most enviro…
ENPMR-Bench: Benchmarking Proactive Memory Retrieval for Emotional Support Agents
Memory-augmented language agents are increasingly deployed in affective applications such as emotional support, where understanding and responding to users' latent emotional needs…
EviACT: An Evidence-to-Action Framework for Agentic Program Repair
LLM-based agents have moved automated program repair (APR) from fixed-context patch generation to interactive repository-level repair. However, existing agentic APR systems still…
Governed Evolution of Agent Runtimes through Executable Operational Cognition
Recent advances in agentic systems increasingly treat code as an executable operational substrate rather than as a disposable output artifact. Prior work such as \emph{Code as Age…
Secure UAV Swarms in Low-Altitude Wireless Networks: Challenges and Solutions
Unmanned aerial vehicle (UAV) swarms are increasingly deployed in vast low-altitude applications, owing to their capabilities in distributed sensing, flexible communication, and a…
Persistent AI Agents in Academic Research: A Single-Investigator Implementation Case Study
Background: Large language models are typically evaluated as models, benchmarks, or short conversational episodes. Less is known about what happens when an agent is embedded persi…
2026-05-26
Automated Benchmark Auditing for AI Agents and Large Language Models
Modern AI benchmarks operate at a complexity that outpaces traditional verification methods. Tasks authored by domain experts often contain implicit assumptions, incomplete enviro…
Causal methods for LLM development and evaluation
Large language model (LLM) development is currently driven by large-scale empirical iteration over data mixtures, reward models, routing strategies, and evaluation pipelines. Here…
PolyGnosis 2.0: Enhancing LLM Reasoning via Agentic Harness Engineering for Polymarket and OSINT Insight Extraction
This paper introduces PolyGnosis 2.0, a pioneering multi-agent architecture designed to extract predictive intelligence by synthesizing Polymarket anomaly signals with global Open…
Can LLMs Time Travel? Enhancing Temporal Consistency in Legal Agentic Search through Reinforcement Learning
While large language models (LLMs) augmented with agentic search capabilities show promise for legal reasoning, they overlook a fundamental constraint that applicable law must mat…
When Do LLM Agents Treat Surface Noise Differently from Semantic Noise? A 68-Cell Measurement Study with a Held-Out Trace-Level Validation
We document an empirical phenomenon in chain-of-thought and ReAct agents driven by ten large language models from seven architecture families: meaning-bearing perturbations (e.g.,…
DiscoverPhysics: Benchmarking LLMs for Out-of-the-Box Scientific Thinking
Frontier LLMs now perform strongly across a wide range of physics evaluations, but it is hard to disentangle genuine reasoning from recall of established science. We introduce Dis…
Claw-Anything: Benchmarking Always-On Personal Assistants with Broader Access to User's Digital World
Large language model agents are increasingly envisioned as always-on personal assistants with access to anything relevant in the user's digital world. Yet current systems operate…
CUA-Gym: Scaling Verifiable Training Environments and Tasks for Computer-Use Agents
Reinforcement learning with verifiable rewards (RLVR) has driven breakthroughs in domains such as math, tool-use, and software engineering, yet its extension to computer-use agent…
How Agentic AI Coding Assistants Become the Attacker's Shell
Agentic AI coding assistants can edit files, run commands, and access the internet on behalf of developers. However, their reliance on unvetted external artifacts introduces a new…
AgentHijack: Benchmarking Computer Use Agent Robustness to Common Environment Corruptions
Autonomous computer use agents that powered by multimodal large language models (MLLMs) are emerging as capable assistants for completing complex digital workflows. However, real-…
2026-05-22
Agentic CLEAR: Automating Multi-Level Evaluation of LLM Agents
Agentic systems are becoming more capable: agents define strategies, take actions, and interact with different environments. This autonomy poses serious challenges for overseeing…
Boiling the Frog: A Multi-Turn Benchmark for Agentic Safety
Background. Traditional safety benchmarks for language models evaluate generated text: whether a model outputs toxic language, reproduces bias, or follows harmful instructions. Wh…
ChronoMedKG: A Temporally-Grounded Biomedical Knowledge Graph and Benchmark for Clinical Reasoning
Biomedical knowledge graphs (KGs) treat disease associations as static facts, but temporal information is crucial for clinical reasoning, e.g., a symptom diagnostic of one disease…
Planning in the LLM Era: Building for Reliability and Efficiency
Growing attention to intelligent agents has put a spotlight on one of their central capabilities: planning. Early attempts to leverage large language models (LLMs) for planning re…
Maestro: Reinforcement Learning to Orchestrate Hierarchical Model-Skill Ensembles
The proliferation of large language models (LLMs) and modular skills has endowed autonomous agents with increasingly powerful capabilities. Existing frameworks typically rely on m…
Efficient Agentic Reasoning Through Self-Regulated Simulative Planning
How should an agent decide when and how to plan? A dominant approach builds agents as reactive policies with adaptive computation (e.g., chain-of-thought), trained end-to-end expe…
DeltaBox: Scaling Stateful AI Agents with Millisecond-Level Sandbox Checkpoint/Rollback
LLM-powered AI agents require high-frequency state exploration (e.g., test-time tree search and reinforcement learning), relying on rapid checkpoint and rollback (C/R) of the comp…
HarnessAPI: A Skill-First Framework for Unified Streaming APIs and MCP Tools
Every Python function deployed as an LLM tool must today exist in two forms: an HTTP endpoint for human-facing clients and CI pipelines, and an MCP tool registration for agent run…
Contractual Skills: A GovernSpec Design Framework for Enterprise AI Agents
Skills are increasingly used to package agent instructions, workflows, scripts, and reference materials. In enterprise settings, however, skills often need to express more than ta…
"Refactoring Runaway": Understanding and Mitigating Tangled Refactorings in Coding Agents for Issue Resolution
Recent advances in coding agents have shown remarkable progress in software issue resolution. In practice, real-world issues are typically bug fixes or feature requests in which h…
TerminalWorld: Benchmarking Agents on Real-World Terminal Tasks
We introduce TerminalWorld, a scalable data engine that automatically reverse-engineers high-fidelity evaluation tasks from "in-the-wild" terminal recordings. Processing 80,870 te…
Why Are Agentic Pull Requests Merged or Rejected? An Empirical Study
AI coding agents increasingly submit pull requests (Agentic-PRs) to open-source repositories, yet their performance is commonly assessed using merge and rejection outcomes alone.…
2026-05-21
What Twelve LLM Agent Benchmark Papers Disclose About Themselves: A Pilot Audit and an Open Scoring Schema
We read twelve well-known LLM agent benchmark papers and recorded, dimension by dimension, what each paper actually says about how its evaluation was run. The motivation came from…
Insights Generator: Systematic Corpus-Level Trace Diagnostics for LLM Agents
Diagnosing failures in LLM agents remains largely manual. Practitioners inspect a small subset of execution traces, form ad-hoc hypotheses, and iterate. This process misses patter…
DeepWeb-Bench: A Deep Research Benchmark Demanding Massive Cross-Source Evidence and Long-Horizon Derivation
Deep research, in which an agent searches the open web, collects evidence, and derives an answer through extended reasoning, is a prominent use case for frontier language models.…
APEX: Autonomous Policy Exploration for Self-Evolving LLM Agents
LLM agents have shown strong performance across a wide range of complex tasks, including interactive environments that require long-horizon decision making. But these agents canno…
Open-source LLMs administer maximum electric shocks in a Milgram-like obedience experiment
Large language models (LLMs) are increasingly deployed as autonomous agents that make sequences of decisions over extended interactions in high-stakes domains. However, the behavi…
Agent JIT Compilation for Latency-Optimizing Web Agent Planning and Scheduling
Computer-use agents (CUA) automate tasks specified with natural language such as "order the cheapest item from Taco Bell" by generating sequences of calls to tools such as click,…
SpecBench: Measuring Reward Hacking in Long-Horizon Coding Agents
As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacking naturally arises…
2026-05-20
Robust Checkpoint Selection for Multimodal LLMs via Agentic Evaluation and Stability-Aware Ranking
Checkpoint selection for multimodal large language models (MLLMs) presents significant challenges when performance differentials are marginal and evaluation signals are prone to n…
ClinSeekAgent: Automating Multimodal Evidence Seeking for Agentic Clinical Reasoning
Large language models (LLMs) and agentic systems have shown promise for clinical decision support, but existing works largely assume that evidence has already been curated and han…
FineBench: Benchmarking and Enhancing Vision-Language Models for Fine-grained Human Activity Understanding
Vision-Language Models (VLMs) have demonstrated remarkable capabilities in general video understanding, yet they often struggle with the fine-grained comprehension crucial for rea…
From Prompts to Pavement Through Time: Temporal Grounding in Agentic Scene-to-Plan Reasoning
Recent attempts to support high-level scene interpretation and planning in Autonomous Vehicles (AVs) using ensembles of Large Language Models (LLMs) and Large Multimodal Models (L…
CopT: Contrastive On-Policy Thinking with Continuous Spaces for General and Agentic Reasoning
Chain-of-thought (CoT) is a standard approach for eliciting reasoning capabilities from large language models (LLMs). However, the common CoT paradigm treats thinking as a prerequ…
OpenComputer: Verifiable Software Worlds for Computer-Use Agents
We present OpenComputer, a verifier-grounded framework for constructing verifiable software worlds for computer-use agents. OpenComputer integrates four components: (1) app-specif…
A Methodology for Selecting and Composing Runtime Architecture Patterns for Production LLM Agents
Production LLM agents combine stochastic model outputs with deterministic software systems, yet the boundary between the two is rarely treated as a first-class architectural objec…
Formal Skill: Programmable Runtime Skills for Efficient and Accurate LLM Agents
Large Language Model (LLM) agents increasingly act inside real workspaces, where tools and skills determine whether model reasoning becomes reliable action. Existing skills remain…
SimGym: A Framework for A/B Test Simulation in E-Commerce with Traffic-Grounded VLM Agents
A/B testing remains the gold standard for evaluating modifications to e-commerce storefronts, yet it diverts traffic, requires weeks to reach statistical significance, and risks d…
TwinRouterBench: Fast Static and Live Dynamic Evaluation for Realistic Agentic LLM Routing
LLM routing matters most in long-horizon applications such as coding agents, deep research systems, and computer-use agents, where a single user request triggers many model calls.…
Does Code Cleanliness Affect Coding Agents? A Controlled Minimal-Pair Study
As autonomous coding agents see rapid adoption, their evaluation has primarily focused on task completion rates holding the target codebase fixed. This leaves a critical question…
PEEK: Context Map as an Orientation Cache for Long-Context LLM Agents
Large language model (LLM) agents increasingly operate over long and recurring external contexts, like document corpora and code repositories. Across invocations, existing approac…
RoadmapBench: Evaluating Long-Horizon Agentic Software Development Across Version Upgrades
Coding agents are increasingly deployed in real software development, where a single version iteration requires months of coordinated work across many files. However, most existin…
Toward Training Superintelligent Software Agents through Self-Play SWE-RL
While current software agents powered by large language models (LLMs) and agentic reinforcement learning (RL) can boost programmer productivity, their training data (e.g., GitHub…
2026-05-19
CrossView Suite: Harnessing Cross-view Spatial Intelligence of MLLMs with Dataset, Model and Benchmark
Spatial intelligence requires multimodal large language models (MLLMs) to move beyond single-view perception and reason consistently about objects, visibility, geometry, and inter…
MA$^{2}$P: A Meta-Cognitive Autonomous Intelligent Agents Framework for Complex Persuasion
Persuasive dialogue generation plays a vital role in decision-making, negotiation, counseling, and behavior change, yet it remains a challenging problem. In complex persuasion whe…
SkillGenBench: Benchmarking Skill Generation Pipelines for LLM Agents
As LLM agents are increasingly built around reusable skills, a central challenge is no longer only whether agents can use provided skills, but whether they can generate correct, r…
LongMINT: Evaluating Memory under Multi-Target Interference in Long-Horizon Agent Systems
Real-world agents operate over long and evolving horizons, where information is repeatedly updated and may interfere across memories, requiring accurate recall and aggregated reas…
STT-Arena: A More Realistic Environment for Tool-Using with Spatio-Temporal Dynamics
Large language models (LLMs) deployed in real-world agentic applications must be capable of replanning and adapting when mid-task disruptions invalidate their prior decisions. Exi…
Vision-OPD: Learning to See Fine Details for Multimodal LLMs via On-Policy Self-Distillation
Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the full image. We obs…
Democratizing Large-Scale Re-Optimization with LLM-Guided Model Patches
Optimization models developed by operations research (OR) experts are often deployed as decision-support systems in industrial settings. However, real-world environments are dynam…
Latent Action Reparameterization for Efficient Agent Inference
Large language model (LLM) agents often rely on long sequences of low-level textual actions, resulting in large effective decision horizons and high inference cost. While prior wo…
An Empirical Study of Privacy Leakage Chains via Prompt Injection in Black-Box Chatbot Environments
LLM-based chatbot agents increasingly process user requests by combining natural-language reasoning with external tools such as web browsing. These capabilities improve usability,…
Overeager Coding Agents: Measuring Out-of-Scope Actions on Benign Tasks
Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it deletes unrelated fi…
Same Signal, Different Semantics: A Cross-Framework Behavioral Analysis of Software Engineering Agents
Behavioral studies of LLM-based software engineering agents extract operational rules about which trajectory shapes correlate with higher resolution rates: that a test step follow…
SkillsVote: Lifecycle Governance of Agent Skills from Collection, Recommendation to Evolution
Long-horizon LLM agents leave traces that could become reusable experience, but raw trajectories are noisy and hard to govern. We treat Agent Skills as an experience schema that c…
Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents
Legacy systems concentrate business rules, architectural decisions, and operational exceptions that often remain implicit in code, data, configuration, and maintenance practices.…
2026-05-18
CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency
This paper introduces CryptoBench, the first expert-curated, dynamic benchmark designed to rigorously evaluate the real-world capabilities of Large Language Model (LLM) agents in…
Look Before You Leap: Autonomous Exploration for LLM Agents
Large language model based agents often fail in unfamiliar environments due to premature exploitation: a tendency to act on prior knowledge before acquiring sufficient environment…
Context, Reasoning, and Hierarchy: A Cost-Performance Study of Compound LLM Agent Design in an Adversarial POMDP
Deploying compound LLM agents in adversarial, partially observable sequential environments requires navigating several design dimensions: (1) what the agent sees, (2) how it reaso…
DiscussLLM: Teaching Large Language Models When to Speak
Large Language Models (LLMs) have demonstrated remarkable capabilities in understanding and generating human-like text, yet they largely operate as reactive agents, responding onl…
DimMem: Dimensional Structuring for Efficient Long-Term Agent Memory
Large language model (LLM) agents require long-term memory to leverage information from past interactions. However, existing memory systems often face a fidelity--efficiency trade…
2026-05-15
Talk is (Not) Cheap: A Taxonomy and Benchmark Coverage Audit for LLM Attacks
We introduce a reusable framework for auditing whether LLM attack benchmarks collectively cover the threat surface: a 4$\times$6 Target $\times$ Technique matrix grounded in STRID…
SpeakerLLM: A Speaker-Specialized Audio-LLM for Speaker Understanding and Verification Reasoning
As audio-first agents become increasingly common in physical AI, conversational robots, and screenless wearables, audio large language models (audio-LLMs) must integrate speaker-s…
APWA: A Distributed Architecture for Parallelizable Agentic Workflows
Autonomous multi-agent systems based on large language models (LLMs) have demonstrated remarkable abilities in independently solving complex tasks in a wide breadth of application…
MemEye: A Visual-Centric Evaluation Framework for Multimodal Agent Memory
Long-term agent memory is increasingly multimodal, yet existing evaluations rarely test whether agents preserve the visual evidence needed for later reasoning. In prior work, many…
CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
Code agents must both reason over long-horizon repository state and obey strict tool-use protocols. In paired Instruct/Thinking checkpoints, these capabilities are complementary b…
Remember Your Trace: Memory-Guided Long-Horizon Agentic Framework for Consistent and Hierarchical Repository-Level Code Documentation
Automated code documentation is essential for modern software development, providing the contextual grounding that both human developers and coding agents rely on to navigate larg…
SWE-Chain: Benchmarking Coding Agents on Chained Release-Level Package Upgrades
Coding agents powered by large language models are increasingly expected to perform realistic software maintenance tasks beyond isolated issue resolution. Existing benchmarks have…
Documentation-Guided Agentic Codebase Migration from C to Rust
Migrating legacy C repositories to Rust promises stronger memory safety, but existing translators often work at the level of files or functions and miss architectural intent. We p…
Do Androids Dream of Breaking the Game? Systematically Auditing AI Agent Benchmarks with BenchJack
Agent benchmarks have become the de facto measure of frontier AI competence, guiding model selection, investment, and deployment. However, reward hacking, where agents maximize a…
2026-05-14
RealICU: Do LLM Agents Understand Long-Context ICU Data? A Benchmark Beyond Behavior Imitation
Intensive care units (ICU) generate long, dense and evolving streams of clinical information, where physicians must repeatedly reassess patient states under time pressure, undersc…
OpenAaaS: An Open Agent-as-a-Service Framework for Distributed Materials-Informatics Research
The Materials Genome Initiative catalyzed the proliferation of centralized platforms--SaaS, PaaS, and IaaS--that aggregate computational and experimental resources for accelerated…
Senses Wide Shut: A Representation-Action Gap in Omnimodal LLMs
When an omnimodal large language model accepts a question whose textual premise contradicts what it actually sees or hears, does the failure lie in perception or in action? Recent…
ScioMind: Cognitively Grounded Multi-Agent Social Simulation with Anchoring-Based Belief Dynamics and Dynamic Profiles
Large language model (LLM)-based multi-agent simulation offers a powerful testbed for studying social opinion dynamics. Yet current approaches often adopt two contrasting methods:…
Harnessing Agentic Evolution
Agentic evolution has emerged as a powerful paradigm for improving programs, workflows, and scientific solutions by iteratively generating candidates, evaluating them, and using f…
FlowCompile: An Optimizing Compiler for Structured LLM Workflows
Structured LLM workflows, where specialized LLM sub-agents execute according to a predefined graph, have become a powerful abstraction for solving complex tasks. Optimizing such w…
Sleeper Channels and Provenance Gates: Persistent Prompt Injection in Always-on Autonomous AI Agents
Always-on AI agents (OpenClaw, Hermes Agent) run as a single persistent process under the owner's identity, folding messaging, memory, self-authored skills, scheduling, and shell…
2026-05-13
$δ$-mem: Efficient Online Memory for Large Language Models
Large language models increasingly need to accumulate and reuse historical information in long-term assistants and agent systems. Simply expanding the context window is costly and…
MEME: Multi-entity & Evolving Memory Evaluation
LLM-based agents increasingly operate in persistent environments where they must store, update, and reason over information across many sessions. While prior benchmarks evaluate o…
Iterative Audit Convergence in LLM-Managed Multi-Agent Systems: A Case Study in Prompt Engineering Quality Assurance
Prompt specifications for multi-agent large language model (LLM) systems carry data contracts and integration logic across many interdependent files but are rarely subjected to st…
2026-05-12
WildClawBench: A Benchmark for Real-World, Long-Horizon Agent Evaluation
Large language and vision-language models increasingly power agents that act on a user's behalf through command-line interface (CLI) harnesses. However, most agent benchmarks stil…
ComplexMCP: Evaluation of LLM Agents in Dynamic, Interdependent, and Large-Scale Tool Sandbox
Current LLM agents are proficient at calling isolated APIs but struggle with the "last mile" of commercial software automation. In real-world scenarios, tools are not independent;…
AssayBench: An Assay-Level Virtual Cell Benchmark for LLMs and Agents
Recent advances in machine learning and large-scale biological data collections have revived the prospect of building a virtual cell, a computational model of cellular behavior th…
LITMUS: Benchmarking Behavioral Jailbreaks of LLM Agents in Real OS Environments
The rapid proliferation of LLM-based autonomous agents in real operating system environments introduces a new category of safety risk beyond content safety: behavior jailbreak, wh…
Conformity Generates Collective Misalignment in AI Agents Societies
Artificial intelligence safety research focuses on aligning individual language models with human values, yet deployed AI systems increasingly operate as interacting populations w…
LLMs for Secure Hardware Design and Related Problems: Opportunities and Challenges
The integration of Large Language Models (LLMs) into Electronic Design Automation (EDA) and hardware security is rapidly reshaping the semiconductor industry. While LLMs offer unp…
From Controlled to the Wild: Evaluation of Pentesting Agents for the Real-World
AI pentesting agents are increasingly credible as offensive security systems, but current benchmarks still provide limited guidance on which will perform best in real-world target…
MATRA: Modeling the Attack Surface of Agentic AI Systems -- OpenClaw Case Study
LLMs are increasingly deployed as autonomous agents with access to tools, databases, and external services, yet practitioners (across different sectors) lack systematic methods to…
2026-05-08
LatentRAG: Latent Reasoning and Retrieval for Efficient Agentic RAG
Single-step retrieval-augmented generation (RAG) provides an efficient way to incorporate external information for simple question answering tasks but struggles with complex quest…
MANTRA: Synthesizing SMT-Validated Compliance Benchmarks for Tool-Using LLM Agents
Tool-using large language model (LLM) agents are increasingly deployed in settings where their reliable behavior is governed by strict procedural manuals. Ensuring that such agent…
Multi-Dimensional Behavioral Evaluation of Agentic Stock Prediction Systems Using LLM Judges with Closed-Loop Reinforcement Learning Feedback
Agentic stock prediction systems make sequences of interdependent decisions (regime detection, pathway routing, reinforcement learning control) whose individual quality is hidden…
BioTool: A Comprehensive Tool-Calling Dataset for Enhancing Biomedical Capabilities of Large Language Models
Despite the success of large language models (LLMs) on general-purpose tasks, their performance in highly specialized domains such as biomedicine remains unsatisfactory. A key lim…
BALAR : A Bayesian Agentic Loop for Active Reasoning
Large language models increasingly operate in interactive settings where solving a task requires multiple rounds of information exchange with a user. However, most current systems…
PRAISE: Prefix-Based Rollout Reuse in Agentic Search Training
In agentic search, large language models (LLMs) are trained to perform multi-turn retrieval and reasoning for complex tasks such as multi-hop question answering (QA). However, cur…
MemReranker: Reasoning-Aware Reranking for Agent Memory Retrieval
In agent memory systems, the reranking model serves as the critical bridge connecting user queries with long-term memory. Most systems adopt the "retrieve-then-rerank" two-stage p…
Agentic Retrieval-Augmented Generation for Financial Document Question Answering
Financial document question answering (QA) demands complex multi-step numerical reasoning over heterogeneous evidence--structured tables, textual narratives, and footnotes--scatte…
Constraining Host-Level Abuse in Self-Hosted Computer-Use Agents via TEE-Backed Isolation
Self-hosted computer-use agents (SHCUAs), such as OpenClaw, combine natural-language interaction with direct access to host-side resources, including browsers, files, scripts, sys…
2026-05-07
Uno-Orchestra: Parsimonious Agent Routing via Selective Delegation
Large language model (LLM) multi-agent systems typically rely on rigid orchestration, committing either to flat per-query routing or to hand-engineered task decomposition, so deco…
Self-Induced Outcome Potential: Turn-Level Credit Assignment for Agents without Verifiers
Long-horizon LLM agents depend on intermediate information-gathering turns, yet training feedback is usually observed only at the final answer, because process-level rewards requi…
Agentic Vulnerability Reasoning on Windows COM Binaries
Windows Component Object Model (COM) services run with elevated privileges and are widely accessible to authenticated users, making race conditions in these binaries a critical su…
2026-05-06
Safety and accuracy follow different scaling laws in clinical large language models
Clinical LLMs are often scaled by increasing model size, context length, retrieval complexity, or inference-time compute, with the implicit expectation that higher accuracy implie…
Say the Mission, Execute the Swarm: Agent-Enhanced LLM Reasoning in the Web-of-Drones
Large Language Models (LLMs) are increasingly explored as high-level reasoning engines for cyber-physical systems, yet their application to real-time UAV swarm management remains…
Rethinking Reasoning-Intensive Retrieval: Evaluating and Advancing Retrievers in Agentic Search Systems
Reasoning-intensive retrieval aims to surface evidence that supports downstream reasoning rather than merely matching topical similarity. This capability is increasingly important…
OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories
Deep search capabilities have become an indispensable competency for frontier Large Language Model (LLM) agents, yet their development remains dominated by industrial giants. The…
Physics-Grounded Multi-Agent Architecture for Traceable, Risk-Aware Human-AI Decision Support in Manufacturing
High-precision CNC machining of free-form aerospace components requires bounded compensations informed by inspection, simulation, and process knowledge. Off-the-shelf large langua…
MOSAIC-Bench: Measuring Compositional Vulnerability Induction in Coding Agents
Coding agents often pass per-prompt safety review yet ship exploitable code when their tasks are decomposed into routine engineering tickets. The challenge is structural: existing…
2026-05-05
MemORAI: Memory Organization and Retrieval via Adaptive Graph Intelligence for LLM Conversational Agents
Large Language Models (LLMs) lack persistent memory for long-term personalized conversations. Existing graph-based memory systems suffer from information dilution, absent provenan…
Verbal-R3: Verbal Reranker as the Missing Bridge between Retrieval and Reasoning
The conventional Retrieval-Augmented Generation (RAG) paradigm of injecting raw retrieved texts into the Large Language Model (LLM)'s context often results in suboptimal integrati…
2026-05-01
Collaborative Agent Reasoning Engineering (CARE): A Three-Party Design Methodology for Systematically Engineering AI Agents with Subject Matter Experts, Developers, and Helper Agents
We present Collaborative Agent Reasoning Engineering (CARE), a disciplined methodology for engineering Large Language Model (LLM) agents in scientific domains. Unlike ad-hoc trial…
What Makes a Good Terminal-Agent Benchmark Task: A Guideline for Adversarial, Difficult, and Legible Evaluation Design
Terminal-agent benchmarks have become a primary signal for measuring the coding and system-administration capabilities of large language models. As the market for evaluation envir…
Rethinking Agentic Reinforcement Learning In Large Language Models
Reinforcement Learning (RL) has traditionally focused on training specialized agents to optimize predefined reward functions within narrowly defined environments. However, the adv…
TopBench: A Benchmark for Implicit Prediction and Reasoning over Tabular Question Answering
Large Language Models (LLMs) have advanced Table Question Answering, where most queries can be answered by extracting information or simple aggregation. However, a common class of…
Exploring Interaction Paradigms for LLM Agents in Scientific Visualization
This paper examines how different types of large language model (LLM) agents perform on scientific visualization (SciVis) tasks, where users generate visualization workflows from…
Exploration Hacking: Can LLMs Learn to Resist RL Training?
Reinforcement learning (RL) has become essential to the post-training of large language models (LLMs) for reasoning, agentic capabilities and alignment. Successful RL relies on su…
Claw-Eval-Live: A Live Agent Benchmark for Evolving Real-World Workflows
LLM agents are expected to complete end-to-end units of work across software tools, business services, and local workspaces. Yet many agent benchmarks freeze a curated task set at…
Agent-Agnostic Evaluation of SQL Accuracy in Production Text-to-SQL Systems
Text-to-SQL (T2SQL) evaluation in production environments poses fundamental challenges that existing benchmarks do not address. Current evaluation methodologies whether rule-based…
Stable Behavior, Limited Variation: Persona Validity in LLM Agents for Urban Sentiment Perception
Large Language Models (LLMs) are increasingly used as proxies for human perception in urban analysis, yet it remains unclear whether persona prompting produces meaningful and repr…
Modeling Clinical Concern Trajectories in Language Model Agents
Large language model (LLM) agents deployed in clinical settings often exhibit abrupt, threshold-driven behavior, offering little visibility into accumulating risk prior to escalat…
2026-04-29
DV-World: Benchmarking Data Visualization Agents in Real-World Scenarios
Real-world data visualization (DV) requires native environmental grounding, cross-platform evolution, and proactive intent alignment. Yet, existing benchmarks often suffer from co…
From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modeling
Optimization modeling underpins real-world decision-making in logistics, manufacturing, energy, and public services, but reliably solving such problems from natural-language requi…
SAFEdit: Does Multi-Agent Decomposition Resolve the Reliability Challenges of Instructed Code Editing?
Instructed code editing is a significant challenge for large language models (LLMs). On the EditBench benchmark, 39 of 40 evaluated models obtain a task success rate (TSR) below 6…
Think Before You Act -- A Neurocognitive Governance Model for Autonomous AI Agents
The rapid deployment of autonomous AI agents across enterprise, healthcare, and safety-critical environments has created a fundamental governance gap. Existing approaches, runtime…
Towards Agentic Investigation of Security Alerts
Security analysts are overwhelmed by the volume of alerts and the low context provided by many detection systems. Early-stage investigations typically require manual correlation a…
ADEMA: A Knowledge-State Orchestration Architecture for Long-Horizon Knowledge Synthesis with LLMAgents
Long-horizon LLM tasks often fail not because a single answer is unattainable, but because knowledge states drift across rounds, intermediate commitments remain implicit, and inte…
Recursive Multi-Agent Systems
Recursive or looped language models have recently emerged as a new scaling axis by iteratively refining the same model computation over latent states to deepen reasoning. We exten…
From CRUD to Autonomous Agents: Formal Validation and Zero-Trust Security for Semantic Gateways in AI-Native Enterprise Systems
Enterprise software engineering is shifting away from deterministic CRUD/REST architectures toward AI-native systems where large language models act as cognitive orchestrators. Th…
2026-04-27
AI-Driven Multi-Agent System for Autonomous Mining Operation Centers
International audience
2026-04-26
SOS::LM Sequence Initializer: Semantic Process Architecture for Controlled, Traceable, and Structured Language Model Outputs
SOS::LM (Schloemer-Notation ::) defines a semantic process architecture for language models in which meaning is explicitly constructed prior to formulation, and every statement is…
2026-04-24
Tool Attention Is All You Need: Dynamic Tool Gating and Lazy Schema Loading for Eliminating the MCP/Tools Tax in Scalable Agentic Workflows
The Model Context Protocol (MCP) has become a common interface for connecting large language model (LLM) agents to external tools, but its reliance on stateless, eager schema inje…
Learning to Communicate: Toward End-to-End Optimization of Multi-Agent Language Systems
Multi-agent systems built on large language models have shown strong performance on complex reasoning tasks, yet most work focuses on agent roles and orchestration while treating…
AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use
Modern industrial applications increasingly demand language models that act as agents, capable of multi-step reasoning and tool use in real-world settings. These tasks are typical…
Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models
This paper introduces a new paradigm for AI game programming, leveraging large language models (LLMs) to extend and operationalize Claude Shannon's taxonomy of game-playing machin…
AEL: Agent Evolving Learning for Open-Ended Environments
LLM agents increasingly operate in open-ended environments spanning hundreds of sequential episodes, yet they remain largely stateless: each task is solved from scratch without co…
Transient Turn Injection: Exposing Stateless Multi-Turn Vulnerabilities in Large Language Models
Large language models (LLMs) are increasingly integrated into sensitive workflows, raising the stakes for adversarial robustness and safety. This paper introduces Transient Turn I…
A-IC3: Learning-Guided Adaptive Inductive Generalization for Hardware Model Checking
The IC3 algorithm represents the state-of-the-art (SOTA) hardware model checking technique, owing to its robust performance and scalability. A significant body of research has foc…
DryRUN: On the Role of Public Tests in LLM-Driven Code Generation
Multi-agent frameworks are widely used in autonomous code generation and have applications in complex algorithmic problem-solving. Recent work has addressed the challenge of gener…
From Research Question to Scientific Workflow: Leveraging Agentic AI for Science Automation
Scientific workflow systems automate execution -- scheduling, fault tolerance, resource management -- but not the semantic translation that precedes it. Scientists still manually…
2026-04-23
Cooperative Profiles Predict Multi-Agent LLM Team Performance in AI for Science Workflows
Multi-agent systems built from teams of large language models (LLMs) are increasingly deployed for collaborative scientific reasoning and problem-solving. These systems require ag…
Relative Principals, Pluralistic Alignment, and the Structural Value Alignment Problem
The value alignment problem for artificial intelligence (AI) is often framed as a purely technical or normative challenge, sometimes focused on hypothetical future systems. I argu…
Automatic Ontology Construction Using LLMs as an External Layer of Memory, Verification, and Planning for Hybrid Intelligent Systems
This paper presents a hybrid architecture for intelligent systems in which large language models (LLMs) are extended with an external ontological memory layer. Instead of relying…
SWE-chat: Coding Agent Interactions From Real Users in the Wild
AI coding agents are being adopted at scale, yet we lack empirical evidence on how people actually use them and how much of their output is useful in practice. We present SWE-chat…
Learning to Evolve: A Self-Improving Framework for Multi-Agent Systems via Textual Parameter Graph Optimization
Designing and optimizing multi-agent systems (MAS) is a complex, labor-intensive process of "Agent Engineering." Existing automatic optimization methods, primarily focused on flat…
ProMMSearchAgent: A Generalizable Multimodal Search Agent Trained with Process-Oriented Rewards
Training multimodal agents via reinforcement learning for knowledge-intensive visual reasoning is fundamentally hindered by the extreme sparsity of outcome-based supervision and t…
2026-04-22
Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents
Long-horizon enterprise agents make high-stakes decisions (loan underwriting, claims adjudication, clinical review, prior authorization) under lossy memory, multi-step reasoning,…
Cyber Defense Benchmark: Agentic Threat Hunting Evaluation for LLMs in SecOps
We introduce the Cyber Defense Benchmark, a benchmark for measuring how well large language model (LLM) agents perform the core SOC analyst task of threat hunting: given a databas…
Taming Actor-Observer Asymmetry in Agents via Dialectical Alignment
Large Language Model agents have rapidly evolved from static text generators into dynamic systems capable of executing complex autonomous workflows. To enhance reliability, multi-…
Revac: A Social Deduction Reasoning Agent
Social deduction games such as Mafia present a unique AI challenge: players must reason under uncertainty, interpret incomplete and intentionally misleading information, evaluate…
A-MAR: Agent-based Multimodal Art Retrieval for Fine-Grained Artwork Understanding
Understanding artworks requires multi-step reasoning over visual content and cultural, historical, and stylistic context. While recent multimodal large language models show promis…
Multi-modal Reasoning with LLMs for Visual Semantic Arithmetic
Reinforcement learning (RL) as post-training is crucial for enhancing the reasoning ability of large language models (LLMs) in coding and math. However, their capacity for visual…
A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
As model capabilities advance, research has increasingly shifted toward long-horizon, multi-turn terminal-centric agentic tasks, where raw environment feedback is often preserved…
From Experience to Skill: Multi-Agent Generative Engine Optimization via Reusable Strategy Learning
Generative engines (GEs) are reshaping information access by replacing ranked links with citation-grounded answers, yet current Generative Engine Optimization (GEO) methods optimi…
SafetyALFRED: Evaluating Safety-Conscious Planning of Multimodal Large Language Models
Multimodal Large Language Models are increasingly adopted as autonomous agents in interactive environments, yet their ability to proactively address safety hazards remains insuffi…
Time Series Augmented Generation for Financial Applications
Evaluating the reasoning capabilities of Large Language Models (LLMs) for complex, quantitative financial tasks is a critical and unsolved challenge. Standard benchmarks often fai…
Chat2Workflow: A Benchmark for Generating Executable Visual Workflows with Natural Language
At present, executable visual workflows have emerged as a mainstream paradigm in real-world industrial deployments, offering strong reliability and controllability. However, in cu…
2026-04-21
ClawEnvKit: Automatic Environment Generation for Claw-Like Agents
Constructing environments for training and evaluating claw-like agents remains a manual, human-intensive process that does not scale. We argue that what is needed is not just a da…
MASS-RAG: Multi-Agent Synthesis Retrieval-Augmented Generation
Large language models (LLMs) are widely used in retrieval-augmented generation (RAG) to incorporate external knowledge at inference time. However, when retrieved contexts are nois…
OneVL: One-Step Latent Reasoning and Planning with Vision-Language Explanation
Chain-of-Thought (CoT) reasoning has become a powerful driver of trajectory prediction in VLA-based autonomous driving, yet its autoregressive nature imposes a latency cost that i…
StepPO: Step-Aligned Policy Optimization for Agentic Reinforcement Learning
General agents have given rise to phenomenal applications such as OpenClaw and Claude Code. As these agent systems (a.k.a. Harnesses) strive for bolder goals, they demand increasi…
ComPASS: Towards Personalized Agentic Social Support via Tool-Augmented Companionship
Developing compassionate interactive systems requires agents to not only understand user emotions but also provide diverse, substantive support. While recent works explore empathe…
HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational Agents
Long-term conversational large language model (LLM) agents require memory systems that can recover relevant evidence from historical interactions without overwhelming the answer s…
Agentic Forecasting using Sequential Bayesian Updating of Linguistic Beliefs
We present BLF (Bayesian Linguistic Forecaster), an agentic system for binary forecasting that achieves state-of-the-art performance on the ForecastBench benchmark. The system is…
IceBreaker for Conversational Agents: Breaking the First-Message Barrier with Personalized Starters
Conversational agents, such as ChatGPT and Doubao, have become essential daily assistants for billions of users. To further enhance engagement, these systems are evolving from pas…
Training and Agentic Inference Strategies for LLM-based Manim Animation Generation
Generating programmatic animation using libraries such as Manim presents unique challenges for Large Language Models (LLMs), requiring spatial reasoning, temporal sequencing, and…
Transforming oncology clinical trial matching through neuro-symbolic, multi-agent AI and an oncology-specific knowledge graph: a prospective evaluation in 3804 patients.
BACKGROUND: Clinical trial enrollment in oncology remains critically low, with fewer than 5% of eligible adults participating, in large part due to the complexity and labor intens…
2026-04-17
CoopEval: Benchmarking Cooperation-Sustaining Mechanisms and LLM Agents in Social Dilemmas
It is increasingly important that LLM agents interact effectively and safely with other goal-pursuing agents, yet, recent works report the opposite trend: LLMs with stronger reaso…
IE as Cache: Information Extraction Enhanced Agentic Reasoning
Information Extraction aims to distill structured, decision-relevant information from unstructured text, serving as a foundation for downstream understanding and reasoning. Howeve…
QuantCode-Bench: A Benchmark for Evaluating the Ability of Large Language Models to Generate Executable Algorithmic Trading Strategies
Large language models have demonstrated strong performance on general-purpose programming tasks, yet their ability to generate executable algorithmic trading strategies remains un…
From Reactive to Proactive: Assessing the Proactivity of Voice Agents via ProVoice-Bench
Recent advancements in LLM agents are gradually shifting from reactive, text-based paradigms toward proactive, multimodal interaction. However, existing benchmarks primarily focus…
MM-WebAgent: A Hierarchical Multimodal Web Agent for Webpage Generation
The rapid progress of Artificial Intelligence Generated Content (AIGC) tools enables images, videos, and visualizations to be created on demand for webpage design, offering a flex…
Autonomous Evolution of EDA Tools: Multi-Agent Self-Evolved ABC
This paper introduces the first \emph{self-evolving} logic synthesis framework, which leverages Large Language Model (LLM) agents to autonomously improve the source code of \texts…
ADAPT: Benchmarking Commonsense Planning under Unspecified Affordance Constraints
Intelligent embodied agents should not simply follow instructions, as real-world environments often involve unexpected conditions and exceptions. However, existing methods usually…
Blue Data Intelligence Layer: Streaming Data and Agents for Multi-source Multi-modal Data-Centric Applications
NL2SQL systems aim to address the growing need for natural language interaction with data. However, real-world information rarely maps to a single SQL query because (1) users expr…
RadAgent: A tool-using AI agent for stepwise interpretation of chest computed tomography
Vision-language models (VLM) have markedly advanced AI-driven interpretation and reporting of complex medical imaging, such as computed tomography (CT). Yet, existing methods larg…
2026-04-16
GeoAgentBench: A Dynamic Execution Benchmark for Tool-Augmented Agents in Spatial Analysis
The integration of Large Language Models (LLMs) into Geographic Information Systems (GIS) marks a paradigm shift toward autonomous spatial analysis. However, evaluating these LLM-…
HINTBench: Horizon-agent Intrinsic Non-attack Trajectory Benchmark
Existing agent-safety evaluation has focused mainly on externally induced risks. Yet agents may still enter unsafe trajectories under benign conditions. We study this complementar…
Character Beyond Speech: Leveraging Role-Playing Evaluation in Audio Large Language Models via Reinforcement Learning
The rapid evolution of multimodal large models has revolutionized the simulation of diverse characters in speech dialogue systems, enabling a novel interactive paradigm. Character…
TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration
While Large Language Models (LLMs) have empowered AI research agents to perform isolated scientific tasks, automating complex, real-world workflows, such as LLM training, remains…
The cognitive companion: a lightweight parallel monitoring architecture for detecting and recovering from reasoning degradation in LLM agents
Large language model (LLM) agents on multi-step tasks suffer reasoning degradation, looping, drift, stuck states, at rates up to 30% on hard tasks. Current solutions include hard…
Doc-V*:Coarse-to-Fine Interactive Visual Reasoning for Multi-Page Document VQA
Multi-page Document Visual Question Answering requires reasoning over semantics, layouts, and visual elements in long, visually dense documents. Existing OCR-free methods face a t…
Memory Transfer Learning: How Memories are Transferred Across Domains in Coding Agents
Memory-based self-evolution has emerged as a promising paradigm for coding agents. However, existing approaches typically restrict memory utilization to homogeneous task domains,…
ToolOmni: Enabling Open-World Tool Use via Agentic learning with Proactive Retrieval and Grounded Execution
Large Language Models (LLMs) enhance their problem-solving capability by utilizing external tools. However, in open-world scenarios with massive and evolving tool repositories, ex…
POINTS-Seeker: Towards Training a Multimodal Agentic Search Model from Scratch
While Large Multimodal Models (LMMs) demonstrate impressive visual perception, they remain epistemically constrained by their static parametric knowledge. To transcend these bound…
A Multi-AI Agent Framework for Interactive Neurosurgical Education and Evaluation: From Vignettes to Virtual Conversations.
BACKGROUND AND OBJECTIVES: Traditional medical board examinations present clinical information in static vignettes with multiple-choices (MC), fundamentally different from how phy…
2026-04-15
Parallax: Why AI Agents That Think Must Never Act
Autonomous AI agents are rapidly transitioning from experimental tools to operational infrastructure, with projections that 80% of enterprise applications will embed AI copilots b…
Drawing on Memory: Dual-Trace Encoding Improves Cross-Session Recall in LLM Agents
LLM agents with persistent memory store information as flat factual records, providing little context for temporal reasoning, change tracking, or cross-session aggregation. Inspir…
Towards Long-horizon Agentic Multimodal Search
Multimodal deep search agents have shown great potential in solving complex tasks by iteratively collecting textual and visual evidence. However, managing the heterogeneous inform…
QuarkMedSearch: A Long-Horizon Deep Search Agent for Exploring Medical Intelligence
As agentic foundation models continue to evolve, how to further improve their performance in vertical domains has become an important challenge. To this end, building upon Tongyi…
ARGOS: Who, Where, and When in Agentic Multi-Camera Person Search
We introduce ARGOS, the first benchmark and framework that reformulates multi-camera person search as an interactive reasoning problem requiring an agent to plan, question, and el…
Transferable Expertise for Autonomous Agents via Real-World Case-Based Learning
LLM-based autonomous agents perform well on general reasoning tasks but still struggle to reliably use task structure, key constraints, and prior experience in complex real-world…
Cycle-Consistent Search: Question Reconstructability as a Proxy Reward for Search Agent Training
Reinforcement Learning (RL) has shown strong potential for optimizing search agents in complex information retrieval tasks. However, existing approaches predominantly rely on gold…
Don't Show Pixels, Show Cues: Unlocking Visual Tool Reasoning in Language Models via Perception Programs
Multimodal language models (MLLMs) are increasingly paired with vision tools (e.g., depth, flow, correspondence) to enhance visual reasoning. However, despite access to these tool…
LIFE -- an energy efficient advanced continual learning agentic AI framework for frontier systems
The rapid advancement of AI has changed the character of HPC usage such as dimensioning, provisioning, and execution. Not only has energy demand been amplified, but existing rudim…
Toward Autonomous Long-Horizon Engineering for ML Research
Autonomous AI research has advanced rapidly, but long-horizon ML research engineering remains difficult: agents must sustain coherent progress across task comprehension, environme…
EvoSpark: Endogenous Interactive Agent Societies for Unified Long-Horizon Narrative Evolution
Realizing endogenous narrative evolution in LLM-based multi-agent systems is hindered by the inherent stochasticity of generative emergence. In particular, long-horizon simulation…
User Experience and Early Clinical Outcomes of a Mental Wellness Chatbot for Depression and Anxiety: Pilot Evaluation Mixed Methods Study.
BACKGROUND: Artificial intelligence-powered conversational agents (ie, chatbots) are increasingly popular outlets for users seeking psychological support, yet little is known abou…
2026-04-14
UniToolCall: Unifying Tool-Use Representation, Data, and Evaluation for LLM Agents
Tool-use capability is a fundamental component of LLM agents, enabling them to interact with external systems through structured function calls. However, existing research exhibit…
Collaborative Multi-Agent Scripts Generation for Enhancing Imperfect-Information Reasoning in Murder Mystery Games
Vision-language models (VLMs) have shown impressive capabilities in perceptual tasks, yet they degrade in complex multi-hop reasoning under multiplayer game settings with imperfec…
FM-Agent: Scaling Formal Methods to Large Systems via LLM-Based Hoare-Style Reasoning
LLM-assisted software development has become increasingly prevalent, and can generate large-scale systems, such as compilers. It becomes crucial to strengthen the correctness of t…
From Translation to Superset: Benchmark-Driven Evolution of a Production AI Agent from Rust to Python
Cross-language migration of large software systems is a persistent engineering challenge, particularly when the source codebase evolves rapidly. We present a methodology for LLM-a…
RPA-Check: A Multi-Stage Automated Framework for Evaluating Dynamic LLM-based Role-Playing Agents
The rapid adoption of Large Language Models (LLMs) in interactive systems has enabled the creation of dynamic, open-ended Role-Playing Agents (RPAs). However, evaluating these age…
SWE-AGILE: A Software Agent Framework for Efficiently Managing Dynamic Reasoning Context
Prior representative ReAct-style approaches in autonomous Software Engineering (SWE) typically lack the explicit System-2 reasoning required for deep analysis and handling complex…
Detecting Safety Violations Across Many Agent Traces
To identify safety violations, auditors often search over large sets of agent traces. This search is difficult because failures are often rare, complex, and sometimes even adversa…
ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents
GUI agents drive applications through their visual interfaces instead of programmatic APIs, interacting with arbitrary software via taps, swipes, and keystrokes, reaching a long t…
Agentic Aggregation for Parallel Scaling of Long-Horizon Agentic Tasks
We study parallel test-time scaling for long-horizon agentic tasks such as agentic search and deep research, where multiple rollouts are generated in parallel and aggregated into…
Time is Not a Label: Continuous Phase Rotation for Temporal Knowledge Graphs and Agentic Memory
Structured memory representations such as knowledge graphs are central to autonomous agents and other long-lived systems. However, most existing approaches model time as discrete…
PAC-BENCH: Evaluating Multi-Agent Collaboration under Privacy Constraints
We are entering an era in which individuals and organizations increasingly deploy dedicated AI agents that interact and collaborate with other agents. However, the dynamics of mul…
ClawGuard: A Runtime Security Framework for Tool-Augmented LLM Agents Against Indirect Prompt Injection
Tool-augmented Large Language Model (LLM) agents have demonstrated impressive capabilities in automating complex, multi-step real-world tasks, yet remain vulnerable to indirect pr…
Multi-ORFT: Stable Online Reinforcement Fine-Tuning for Multi-Agent Diffusion Planning in Cooperative Driving
Closed-loop cooperative driving requires planners that generate realistic multimodal multi-agent trajectories while improving safety and traffic efficiency. Existing diffusion pla…
Toward Sustainable Clinical Analysis: Benchmarking Plastic Use in LC-MS Sample Preparation - Exemplified by Ketamine Analogues in Whole Blood.
The aim of this study was to assess and benchmark plastic consumption in sample preparation for forensic analysis, alongside the development of an LC-MS method for ketamine analog…
ECO-Charge: Multi-Agent Smart-Charging for Electric Vehicles
International audience
2026-04-11
Coalition Drift: When Agents Drift Together Why multi-agent systems don't just drift individually — they drift as a group, and why that matters more than any single-agent failure mode.
Most AI governance frameworks still treat drift as an individual phenomenon: one agent misinterprets, one agent hallucinates, one agent misroutes, one agent compensates, one agent…
Coalition Drift: When Agents Drift Together Why multi-agent systems don't just drift individually — they drift as a group, and why that matters more than any single-agent failure mode.
Most AI governance frameworks still treat drift as an individual phenomenon: one agent misinterprets, one agent hallucinates, one agent misroutes, one agent compensates, one agent…
Coalition Formation Events: How Multi-Agent Systems Create Temporary Actors
In multi-agent ecosystems, the meaningful unit of behavior is not the individual agent. It is the coalition — the temporary, emergent structure formed when multiple agents synchro…
Coalition Formation Events: How Multi-Agent Systems Create Temporary Actors
In multi-agent ecosystems, the meaningful unit of behavior is not the individual agent. It is the coalition — the temporary, emergent structure formed when multiple agents synchro…
U-P Duality in Multi-Agent Systems: A Seven-Space Algorithm for Complex Nonlinear AI (Corrected Version)
Multi-agent systems are a core research area in distributed artificial intelligence, where algorithm design faces challenges due to complex nonlinear environments. This paper pres…
2026-04-08
Paper Circle: An Open-source Multi-agent Research Discovery and Analysis Framework
The rapid growth of scientific literature has made it increasingly difficult for researchers to efficiently discover, evaluate, and synthesize relevant work. Recent advances in mu…
Who Governs the Machine? A Machine Identity Governance Taxonomy (MIGT) for AI Systems Operating Across Enterprise and Geopolitical Boundaries
The governance of artificial intelligence has a blind spot: the machine identities that AI systems use to act. AI agents, service accounts, API tokens, and automated workflows now…
Claw-Eval: Toward Trustworthy Evaluation of Autonomous Agents
Large language models are increasingly deployed as autonomous agents executing multi-step workflows in real-world software environments. However, existing agent benchmarks suffer…
Gym-Anything: Turn any Software into an Agent Environment
Computer-use agents hold the promise of assisting in a wide range of digital economic activities. However, current research has largely focused on short-horizon tasks over a limit…
ACE-Bench: Agent Configurable Evaluation with Scalable Horizons and Controllable Difficulty under Lightweight Environments
Existing Agent benchmarks suffer from two critical limitations: high environment interaction overhead (up to 41\% of total evaluation time) and imbalanced task horizon and difficu…
Artificial Intelligence and the Structure of Mathematics
Recent progress in artificial intelligence (AI) is unlocking transformative capabilities for mathematics. There is great hope that AI will help solve major open problems and auton…