2 papers
cs.CL2026
RAG-Stress: Probing the Limits of Evidence Reliance in Retrieval-Augmented Generation
Shunyuan Zhou, Hao Chen, Tianyu Wang +3
Following retrieved evidence does not guarantee factual correctness: misleading evidence can induce a model to replace an answer it previously gave correctly. Standard accuracy mea…
cs.SE2026
CheckerBench: Can Long-Horizon Agents Synthesize Static-Analysis Checkers?
Hang He, Li Wang, Hao Chen +9
Static-analysis checker synthesis requires agents to interpret a defect specification, inspect a repository, implement analyzer-specific logic, and refine the checker through repea…