CMI-Mem: Toward Generalizable Long-Term Memory Management via CMI-Augmented Reinforcement Learning

Abstract:Memory Manager models are pivotal in agent systems. Existing methods rely predominantly on LLM-judged synthetic question-answer (QA) pairs, making memory valuation dependent on sampled queries and the downstream reader. To address this limitation, we propose \textbf{CMI-Mem}, a reinforcement learning(RL)-based lightweight memory manager model with a hybrid reward that combines downstream QA correctness and intrinsic Conditional Mutual Information (CMI). CMI evaluates the information contributed by new conversational inputs relative to the current memory state without conditioning on a sampled QA query, thereby complementing rather than replacing QA grounding. Our codes are available at: this https URL , and the CMI-Mem-4B model checkpoint is available at: this https URL

Artificial Intelligence (cs.AI); Computation and Language (cs.CL)

arXiv:2607.20553 [cs.AI]

(or arXiv:2607.20553v1 [cs.AI] for this version)

https://doi.org/10.48550/arXiv.2607.20553 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.