{"ID":5935665,"CreatedAt":"2026-07-07T01:22:02.77346169Z","UpdatedAt":"2026-07-07T02:10:06.972658124Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.03473","arxiv_id":"2607.03473","title":"MUTE: Return-Preserving Communication Unlearning for Efficient Multi-Agent Coordination","abstract":"Inter-agent communication is critical for coordinating Multi-Agent Reinforcement Learning (MARL) agents under partial observability to perform effectively in cooperative games; however, real-world bandwidth constraints demand sparse interactions. Prior approaches primarily address this trade-off by optimizing information-theoretic surrogates. We argue that these statistical proxies are fundamentally misaligned with the true objective: a message can be highly informative yet irrelevant to the joint return of the task. In this work, we propose Message Unlearning for Targeted Efficiency (MUTE), a framework that views communication reduction as a value-guided machine unlearning problem. MUTE rigorously quantifies the Counterfactual Message Value using an attention-based estimator, and systematically unlearns the transmission of low-value messages from a policy trained without any communication constraints. This is achieved through a dual-objective mechanism that enforces communication sparsity while preserving the return of the original joint policy. We derive a theoretical upper bound on the performance gap induced by this sparsification, guaranteeing controlled return degradation. We also empirically evaluate MUTE on various complex multi-agent environments, achieving 80% to 90% bandwidth reduction while maintaining performance comparable to state-of-the-art baselines.","short_abstract":"Inter-agent communication is critical for coordinating Multi-Agent Reinforcement Learning (MARL) agents under partial observability to perform effectively in cooperative games; however, real-world bandwidth constraints demand sparse interactions. Prior approaches primarily address this trade-off by optimizing informati...","url_abs":"https://arxiv.org/abs/2607.03473","url_pdf":"https://arxiv.org/pdf/2607.03473v1","authors":"[\"Rui Zuo\",\"Qinwei Huang\",\"Mingyang Li\",\"Zhenhang Zhang\",\"Simon Khan\",\"Qinru Qiu\"]","published":"2026-07-03T16:34:19Z","proceeding":"cs.MA","tasks":"[\"cs.MA\"]","methods":"[\"Reinforcement Learning\"]","has_code":false}