RESEARCH

ANNEAL: Adapting LLM Agents via Governed Symbolic Patch Learning

ArXiv cs.AI · Tue, 19 May 2026 04:00:00 GMT

arXiv:2605.16309v1 Announce Type: new Abstract: LLM-based agents can recover from individual execution errors, yet they repeatedly fail on the same fault when the underlying process knowledge--operator schemas, preconditions, and constraints--remains unrepaired. Existing self-evo

Read original source Discuss with A.S.I.S