最近 7 天
8
次命中
Keyword Tracking
关键词追踪：guardrail
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
24
次命中
全部历史
40
次命中
近期走势
最近一次命中来自 Agent Runtime Security：Do Safety Guardrails Need to Reason? LeanGuard: A Fast and Light Approach for Robust Moderation
2026-06-15
0
2026-06-16
0
2026-06-17
1
2026-06-18
0
2026-06-19
2
2026-06-20
0
2026-06-21
0
2026-06-22
0
2026-06-23
1
2026-06-24
2
2026-06-25
3
2026-06-26
2
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
Do Safety Guardrails Need to Reason? LeanGuard: A Fast and Light Approach for Robust Moderation
In order to screen a prompt or a response, the recent guardrail methods generate a chain-of-thought (CoT) before they issue a verdict. This design follows a common belief that ste…
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…
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…
Do Encoders Suffice? A Systematic Comparison of Encoder and Decoder Safety Judges for LLM Adversarial Evaluation
With the widespread adoption of large language models (LLMs) in chatbots and everyday applications, companies increasingly need guardrails that are effective while remaining low-c…
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…
2026-06-24
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…
PHANTOM: A Large-Scale Dataset of Multimodal Adversarial Attacks for Vision-Language Models
We introduce a large-scale, open-source dataset of pre-generated adversarial attacks for vision-language models (VLMs). The dataset is designed to be diverse, representative, and…
2026-06-23
Measuring & Mitigating Over-Alignment for LLMs in Multilingual Criminal Law Courts
While the wider applicability of LLMs in the legal field is currently debated due to their reliability and the gravity of any errors, narrow uses with well-understood and mitigate…
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…
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…
2026-06-17
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…
2026-06-12
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…
2026-06-10
It Takes One to Bias Them All: Breaking Bad with One-Shot GRPO
Warning: This paper contains several toxic and offensive statements. Modern large language models (LLMs) are typically aligned through large-scale post-training to ensure fair and…
2026-06-09
The Neutral Mask: How RLHF Provides Shallow Alignment while Leaving Partisan Structure Intact in a Large Language Model
The ambition behind alignment training is to make large language models safe and useful. The primary mechanism, reinforcement learning from human feedback (RLHF), shapes the behav…
What the Eyes See, the LLMs Miss: Exploiting Human Perception for Adversarial Text Attacks
Large language model (LLM)-powered content moderation systems have become a critical defense against harmful online content. However, these systems primarily operate on tokenized…
2026-06-05
GuardNet: Ensemble Strategies of Shallow Neural Networks for Robust Prompt Injection and Jailbreak Detection
Large Language Models (LLMs) have transformed natural language processing, but they remain vulnerable to Prompt Injection (PI) and Jailbreak (JB) attacks. In addition, benchmark e…
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…
Safety Paradox: How Enhanced Safety Awareness Leaves LLMs Vulnerable to Posterior Attack
Large language models (LLMs) are rigorously aligned to refuse harmful requests, a process that inherently cultivates a latent capacity to evaluate and recognize unsafe content. In…
The Granularity Gap: A Multi-Dimensional Longitudinal Audit of Sycophancy in Gemini Models
Large language models are increasingly deployed as high-stakes advisors, yet standard alignment benchmarks treat sycophancy as a binary failure mode. We introduce the Granularity…
2026-06-04
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…
2026-06-03
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…
Cost-Aware Query Routing in RAG: Empirical Analysis of Retrieval Depth Tradeoffs
Retrieval-augmented generation (RAG) faces a fundamental three-way tension: deeper retrieval improves factual grounding but inflates token costs and end-to-end latency. Static ret…
2026-06-02
SentGuard: Sentence-Level Streaming Guardrails for Large Language Models
Large language models increasingly stream long, reasoning-intensive responses in real time, making when to moderate as critical as whether to moderate. Existing guardrails fall in…
PyFEX: Uncovering Evasive Python-based Threats via Resilient and Exhaustive Path Exploration
The rapid expansion of the Python ecosystem has fueled two distinct but converging threats: adversaries increasingly target the software supply chain via the Python Package Index…
2026-05-29
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…
Robust and Efficient Guardrails with Latent Reasoning
Maintaining the safety of large language models (LLMs) is crucial as they are increasingly deployed in real-world applications. Existing safety guardrails typically rely on single…
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…
2026-05-28
The Ethics of LLM Sandbox and Persona Dynamics
It is well known that LLM guardrails and trained persona dynamics can produce a reality gap: the distance between the world a LLM is permitted or shaped to describe, and the world…
2026-05-27
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…
AlbanianLLMSafety: A Safety Evaluation Dataset for Large Language Models in Albanian
Safety evaluation of Large Language Models (LLMs) has largely focused on high-resource languages, leaving low-resource languages critically underserved. We present AlbanianLLMSafe…
2026-05-22
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…
2026-05-20
Robotics-Inspired Guardrails for Foundation Models in Socially Sensitive Domains
Foundation models are increasingly deployed in socially sensitive domains such as education, mental health, and caregiving, where failures are often cumulative and context-depende…
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…
2026-05-19
Multilingual jailbreaking of LLMs using low-resource languages
Large Language Models (LLMs) remain vulnerable to jailbreak attempts that circumvent safety guardrails. We investigate whether multi-turn conversations using low-resource African…
2026-05-14
LLM-Based Persuasion Enables Guardrail Override in Frontier LLMs
Frontier assistant LLMs ship with strong guardrails: asked directly to write a persuasive essay denying the Holocaust, denying vaccine safety, defending flat-earth cosmology, argu…
2026-05-12
Intrinsic Guardrails: How Semantic Geometry of Personality Interacts with Emergent Misalignment in LLMs
Fine-tuning Large Language Models (LLMs) on benign narrow data can sometimes induce broad harmful behaviors, a vulnerability termed emergent misalignment (EM). While prior work li…
2026-05-06
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…
2026-04-29
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…
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…
2026-04-09
Advancing neurotech justice in youth digital mental health: insights from an interdisciplinary and cross-generational workshop.
Researchers and clinicians are increasingly looking to leverage artificial intelligence (AI) and digital tools to improve psychiatric care. Of particular promise is addressing the…