Back to AI News
arxiv

MAPE Evolves Agent Memory Programs for Better Accuracy at Lower Serving Cost

Researchers introduce MAPE, a framework that evolves complete agent memory programs from minimal seeds using a standardized lifecycle interface and an iterative diagnosis-proposal loop. On LoCoMo and LongMemEval, MAPE reports up to a 12% absolute accuracy gain over manually designed baselines at 35% of the serving cost, with transfer across serving backbones and benchmarks. The work identifies two recurring design patterns: retaining raw conversations as retrievable evidence and composing retrieved evidence according to query intent. Transplanting the composition module into five existing memory systems improved accuracy in all five.

AI Brief

It offers concrete empirical design lessons and an open framework for building more accurate and cost-efficient memory systems for LLM agents.

arXiv:2611.17068v1 Announce Type: cross Abstract: Program evolution provides a promising approach to discover agent memory designs and study the choices underlying their effectiveness. We introduce MAPE, a framework that evolves whole memory programs from minimal seeds through a standardized lifecycle interface and an iterative diagnosis-proposal loop. Experiments on LoCoMo and LongMemEval yield an absolute accuracy gain of up to 12% over manually designed baselines at 35% of the serving cost, with further evaluations supporting transfer across serving backbones and benchmarks. Empirical analyses and ablations identify and validate two recurring design patterns: retaining raw conversations as retrievable evidence preserves details omitted from extracted memories, while composing retrieved evidence according to query intent helps the answering model use it effectively. Transplanting the composition module into five existing memory systems improves accuracy across all five. Beyond these patterns, the search objective shapes where computation goes: optimizing serving cost alongside accuracy shifts computation from LLM-based memory construction to selective processing at query time while retaining competitive accuracy. Together, these findings offer empirical lessons for agent memory design. Code is available at https://github.com/ash-ding/MAPE.
Be the first to rate this article.

Comments & Questions (0)

Captcha
Please be respectful — let's keep the conversation friendly.

No comments yet

Be the first to comment!