Memory Reward Inflation in Self-Improving LLM Agents

본문 미리보기

arXiv:2608.00017v1 Announce Type: new Abstract: Self-improving LLM agents increasingly learn from experience without updating any weights. Each episode is stored in an external memory, scored, and retrieved for similar future tasks to shape later behavior. Viewed through a reward lens, the stored score is a proxy reward for an implicit, non-parametric policy. Each retrieved episode then becomes a policy-improvement step whose reliability hinges on how that score is produced. In deployment, grou