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.
It offers concrete empirical design lessons and an open framework for building more accurate and cost-efficient memory systems for LLM agents.
Comments & Questions (0)
No comments yet
Be the first to comment!