LATIDIA · Investigación

Recordar no es suficiente: refinar la memoria y aprender cuándo usarla en sistemas multiagente.

arXiv: 2610.36652v1Tipo de anuncio: nuevo Resumen: La memoria ayuda a los sistemas multiagente basados en LLM a reutilizar la experiencia, pero los consejos almacenados pueden ser defectuosos o aplicarse en la situación incorrecta. El éxito o el fracaso a nivel de equipo por sí solo no puede

La noticia

arXiv:2610.36652v1 Announce Type: new Abstract: Memory helps LLM-based multi-agent systems reuse experience, but stored advice can be flawed or applied in the wrong situation. Team-level success or failure alone cannot reliably show whether a memory needs correction or should not have been used. We propose DiscernMem, a training-free framework that improves both memory quality and memory use. To improve quality, Defect-Aware Memory Refinement (DMR) compares team executions with a single memory and with no memory, diagnoses rule defects, and tests repairs on current and earlier tasks to guard against losing previously useful behavior. To guide appropriate use, Boundary-Learning Meta-Memory (BLM) records each memory's past uses and effects, learning when its