AI RESEARCH
GRASP: Gated Regression-Aware Skill Proposer for Self-Improving LLM Agents
arXiv CS.AI
•
ArXi:2605.29668v1 Announce Type: new LLM agents acting in structured environments fail in operational rather than conversational ways, and reliability depends on procedural knowledge of the environment. Prior self-improvement methods accumulate natural-language guidance without checking that each new item preserves previously correct behavior, so a note that fixes one trajectory can silently regress another. We