最近 7 天
2
次命中
Keyword Tracking
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 7 天
2
次命中
最近 30 天
3
次命中
全部历史
4
次命中
最近一次命中来自 Terminal and SWE Agents:Smaller Models, Unexpected Costs: Trade-offs in LLM Quantization for Automated Program Repair
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。
Language Models (LLMs) are powerful toolsand have been increasingly adopted for complex software engineering tasks. As the number of parameters increases, results can often be imp…
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…
The development of complex software systems, e.g., cyber-physical systems (CPSs), involves continuous evolution of both system implementations and their requirements. These two ar…
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…