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

[2607.20553] CMI-Mem: Toward Generalizable Long-Term Memory Management via CMI-Augmented Reinforcement Learning Skip to main content Search Submit Donate Log in Computer Science > Artificial Intelligence arXiv:2607.20553 (cs) [Submitted on 15 Jul 2026 ( v1 ), last revised 22 Aug 2026 (this version, v2)] Title: CMI-Mem: Toward Generalizable Long-Term Memory Management via CMI-Augmented Reinforcement Learning Authors: Yubo Wang , Qiuyu Zhao , Zenghui Sun , Shichao Dong , Jinsong Lan , Xiaoyong Zhu , Haoyang Li , Bo Zheng , Lei Chen View PDF HTML (experimental) Abstract: Memory Manager models are pivotal in agent systems. Existing reinforcement-learning methods commonly use LLM-judged synthetic question-answer (QA) pairs: this provides useful downstream task grounding, but values memory through a sampled query distribution and a fixed reader. We propose CMI-Mem, a lightweight RL memory manager with a hybrid reward. Its extrinsic QA term measures end-task correctness, while its intrinsic Conditional Mutual Information (CMI) term evaluates the information contributed by new conversational inputs relative to the current memory state without conditioning on a sampled QA query. The two signals are complementary: QA anchors task utility, whereas CMI provides per-operation supervision for relevant, non-redundant memory construction. Experiments demonstrate improved transfer across memory-use scenarios, together with more efficient training and inference from the per-operation CMI signal. Our codes are available at: this https URL , and the CMI-Mem-4B model checkpoint is available at: this https URL Subjects: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL) Cite as: arXiv:2607.20553 [cs.AI] (or arXiv:2607.20553v2 [cs.AI] for this version) https://doi.org/10.48550/arXiv.2607.20553 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Yubo Wang [ view email ] [v1] Wed, 15 Jul 2026 13:40:24 UTC (929 KB) [v2] Sat, 22 Aug 2026 01:52:47 UTC (948 KB) Full-text links: Access Paper: View PDF HTML (experimental) TeX Source view license Additional Features Audio Summary Current browse context: cs.AI < prev | next > new | recent | 2026-07 Change to browse by: cs cs.CL References & Citations SciX Google Scholar Semantic Scholar export BibTeX citation Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators 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 . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab)

Related documents

• CMI-Mem: Toward Generalizable Long-Term Memory Management via CMI-Augmented Reinforcement Learning#665869
• SPA: A SQL-Plan-Aware Reinforcement Learning Framework for Query Rewriting with LLMs#267757
• Safe Deep Reinforcement Learning for Building Heating Control and Demand-side Flexibility#31320
• SmoothRL: Online Reinforcement Learning During Asynchronous Execution#798397
• SmoothRL: Online Reinforcement Learning During Asynchronous Execution#796984