# MUTE: Return-Preserving Communication Unlearning for Efficient Multi-Agent Coordination

arXiv: https://arxiv.org/abs/2607.03473 · HTML: https://mlsanity.com/paper/2607.03473/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Machine unlearning, one of 12 directions in LLM safety and security.
- Builds on 20 of its 29 references that are in the map.
- First posted on arXiv 3 Jul 2026.

## Placed in

- LLM safety and security / [Machine unlearning](https://mlsanity.com/safety/machine-unlearning/)

## Builds on (most cited first, 20 of 20)

- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [Eternal Sunshine of the Spotless Net: Selective Forgetting in Deep Networks](https://mlsanity.com/paper/1911.04933/) (2019)
- [The StarCraft Multi-Agent Challenge](https://mlsanity.com/paper/1902.04043/) (2019)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [A Survey of Machine Unlearning](https://mlsanity.com/paper/2209.02299/) (2022)
- [TarMAC: Targeted Multi-Agent Communication](https://mlsanity.com/paper/1810.11187/) (2018)
- [Trust Region Policy Optimisation in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2109.11251/) (2021)
- [SMACv2: An Improved Benchmark for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2212.07489/) (2022)
- [Learning when to Communicate at Scale in Multiagent Cooperative and Competitive Tasks](https://mlsanity.com/paper/1812.09755/) (2018)
- [Off-Policy Multi-Agent Decomposed Policy Gradients](https://mlsanity.com/paper/2007.12322/) (2020)
- [Learning Nearly Decomposable Value Functions Via Communication Minimization](https://mlsanity.com/paper/1910.05366/) (2019)
- [Learning Efficient Multi-agent Communication: An Information Bottleneck Approach](https://mlsanity.com/paper/1911.06992/) (2019)
- [Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2408.09675/) (2024)
- [T2MAC: Targeted and Trusted Multi-Agent Communication through Selective Engagement and Evidence-Driven Integration](https://mlsanity.com/paper/2401.10973/) (2024)
- [RGMComm: Return Gap Minimization via Discrete Communications in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2308.03358/) (2023)
- [Towards True Lossless Sparse Communication in Multi-Agent Systems](https://mlsanity.com/paper/2212.00115/) (2022)

## Abstract (arXiv)

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.