Capability-Driven Self-Evolution of Agent Memory

Excerpt

arXiv:2610.06361v1 Announce Type: new Abstract: Memory self-evolution uses task feedback to iteratively improve executable memory programs that store and retrieve information from past interactions. Existing approaches typically adopt holistic evolution, deriving revision directions from mixed feedback and judging progress by overall performance. This can obscure optimization directions and hide capability-specific gains offset by regressions elsewhere, leaving promising directions underexplored