论文 Mitigating Errors in LLM-Generated Web API Invocations via Retrieval-Augmented Generation and Constrained Decoding
论文 When Lower Privileges Suffice: Investigating Over-Privileged Tool Selection in LLM Agents
论文 Beyond Self-Knowledge: Propagating Uncertainty Across Reasoning and Retrieval in LLMs
论文 PACMS: Submodular Context Selection as a Pluggable Engine for LLM Agents
论文 What Does an Evaluation License? A Commit-Bound Census of Claim-Relative Inference in Inspect Evals
论文 To Add Is Machine, To Delete Is Human: Measuring and Mitigating Deletion Avoidance in LLM Code Editing