论文 Mitigating Errors in LLM-Generated Web API Invocations via Retrieval-Augmented Generation and Constrained Decoding
论文 InSight-doc: Agentic Visual Perception for Long-Document Understanding
论文 EvoUndo: Recoverability-Constrained Self-Evolution for LLM Agent Harnesses
论文 Adaptive Critical Token-Aware Retrieval for Repository-Level Code Generation
论文 To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing
论文 What Does an Evaluation License? A Commit-Bound Census of Claim-Relative Inference in Inspect Evals