LATIDIA · Investigación

MemComposer: Aprender a ensamblar memorias para agentes de LLM a través del aprendizaje de refuerzo

arXiv:2610.21091v1 Announce Type: new Resumen: La memoria del agente permite a los agentes del modelo de lenguaje grande (LLM) reutilizar experiencias pasadas sin actualizar sus parámetros. Sin embargo, la similitud semántica por sí sola no me garantiza

La noticia

arXiv:2610.21091v1 Announce Type: new Abstract: Agent memory enables large language model (LLM) agents to reuse past experiences without updating their parameters. However, semantic similarity alone does not guarantee memory usefulness: downstream performance depends on how memories are selected and presented to the agent. We propose MemComposer, a memory composer that jointly examines the current query and retrieved candidates to decide which experiences to include, how many to select, and how to order them. We train the composer using Experience Policy Optimization (ExPO), a GRPO-based framework that evaluates assembled memory contexts through complete agent interactions and uses task-success feedback to optimize the assembly policy. Across three $\tau^2$-bench domains with two frozen