# Decentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding

arXiv: https://arxiv.org/abs/2609.32019 · HTML: https://mlsanity.com/paper/2609.32019/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 42 of its 60 references that are in the map.
- First posted on arXiv 25 Sep 2026.

## Builds on (most cited first, 30 of 42)

- [Attention Is All You Need](https://mlsanity.com/paper/1706.03762/) (2017)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Perceiver: General Perception with Iterative Attention](https://mlsanity.com/paper/2103.03206/) (2021)
- [Learning to Communicate with Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1605.06676/) (2016)
- [Group-in-Group Policy Optimization for LLM Agent Training](https://mlsanity.com/paper/2505.10978/) (2025)
- [Non-Autoregressive Neural Machine Translation](https://mlsanity.com/paper/1711.02281/) (2017)
- [Learning Multiagent Communication with Backpropagation](https://mlsanity.com/paper/1605.07736/) (2016)
- [The Complexity of Decentralized Control of Markov Decision Processes](https://mlsanity.com/paper/1301.3836/) (2013)
- [Multi-Agent Pathfinding: Definitions, Variants, and Benchmarks](https://mlsanity.com/paper/1906.08291/) (2019)
- [GDPO: Group reward-Decoupled Normalization Policy Optimization for Multi-reward RL Optimization](https://mlsanity.com/paper/2601.05242/) (2026)
- [PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning](https://mlsanity.com/paper/1809.03531/) (2018)
- [Searching with Consistent Prioritization for Multi-Agent Path Finding](https://mlsanity.com/paper/1812.06356/) (2018)
- [MADiff: Offline Multi-agent Learning with Diffusion Models](https://mlsanity.com/paper/2305.17330/) (2023)
- [LaCAM: Search-Based Algorithm for Quick Multi-Agent Pathfinding](https://mlsanity.com/paper/2211.13432/) (2022)
- [LLM Collaboration With Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2508.04652/) (2025)
- [Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning](https://mlsanity.com/paper/2011.13219/) (2020)
- [Simultaneous Multi-Robot Motion Planning with Projected Diffusion Models](https://mlsanity.com/paper/2502.03607/) (2025)
- [SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding](https://mlsanity.com/paper/2303.00605/) (2023)
- [Distributed Heuristic Multi-Agent Path Finding with Communication](https://mlsanity.com/paper/2106.11365/) (2021)
- [Learning Selective Communication for Multi-Agent Path Finding](https://mlsanity.com/paper/2109.05413/) (2021)
- [Learn to Follow: Decentralized Lifelong Multi-agent Pathfinding via Planning and Learning](https://mlsanity.com/paper/2310.01207/) (2023)
- [On the Learning of Non-Autoregressive Transformers](https://mlsanity.com/paper/2206.05975/) (2022)
- [POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding](https://mlsanity.com/paper/2407.14931/) (2024)
- [More Centralized Training, Still Decentralized Execution: Multi-Agent Conditional Policy Factorization](https://mlsanity.com/paper/2209.12681/) (2022)
- [MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale](https://mlsanity.com/paper/2409.00134/) (2024)
- [Decentralized Monte Carlo Tree Search for Partially Observable Multi-agent Pathfinding](https://mlsanity.com/paper/2312.15908/) (2023)
- [Work Smarter Not Harder: Simple Imitation Learning with CS-PIBT Outperforms Large Scale Imitation Learning for MAPF](https://mlsanity.com/paper/2409.14491/) (2024)
- [Discrete-Guided Diffusion for Scalable and Safe Multi-Robot Motion Planning](https://mlsanity.com/paper/2508.20095/) (2025)
- [Deploying Ten Thousand Robots: Scalable Imitation Learning for Lifelong Multi-Agent Path Finding](https://mlsanity.com/paper/2410.21415/) (2024)
- [ALPHA: Attention-based Long-horizon Pathfinding in Highly-structured Areas](https://mlsanity.com/paper/2310.08350/) (2023)

## Abstract (arXiv)

Decentralized multi-agent path finding (MAPF) with communication requires agents to reach individual goals without collisions under partial observability. Learnable policies trained on expert data provide an effective approach to this problem. However, when several coordinated joint actions are valid in the same context, independently sampling from per-agent distributions can recombine locally valid choices into incompatible joint actions. This failure can arise from the final sampling mechanism even when the per-agent action distributions are learned correctly. DMM (Decentralized Master-Mind) addresses this by replacing one-shot action sampling with discrete, iterative refinement of action intents across communication rounds, inspired by denoising in diffusion models. Agents initialize random action intents and refine them through local communication, coupling their choices before commitment. DMM is pretrained with imitation learning on expert MAPF solutions and further optimized with MICPO, a critic-free group-relative reinforcement-learning method designed for multi-agent, multi-round action refinement. DMM generally achieves higher success rates and lower solution costs than the evaluated learnable baselines. On 1,600 MovingAI tasks, DMM fine-tuned with MICPO solves 1,598, the highest coverage among the evaluated methods, while achieving solution costs close to those of the strongest baselines. DMM also scales to over one million simultaneously acting agents in obstacle-rich environments. These results show that round-level intent refinement can improve joint-action coordination while preserving decentralized execution.