Decentralized Master-Mind: intent denoising solves 1,598 of 1,600 MAPF tasks and scales to 1M agents
Valeriy Vyaltsev · hf · 2026-10-02
DMM replaces one-shot action sampling in decentralized multi-agent pathfinding with iterative intent refinement across communication rounds, inspired by diffusion denoising. Pretrained with imitation learning and fine-tuned with the critic-free MICPO method, it solves 1,598 of 1,600 MovingAI tasks with near-best solution costs and scales to over one million simultaneously acting agents.
More from Research
- AMap open-sources ABot-Recon: streaming 3D reconstruction from video with a 12-frame local context — rsasaki0109 · 2026-10-02
- Neuralink pretrains decoders on 50,000+ hours of neural data—dataset may be the real moat — CurieuxExplorer · 2026-10-02
- CyberGym cybersecurity benchmark effectively saturated on verified task subset — aryaman2020 · 2026-10-02
- SemEval-2027 Task 9 calls for teams on 4-language multimodal news framing analysis — preslav_nakov · 2026-10-02
- Alternating prompt and model upgrades lift science agent from 42% to 73% — rohanpaul_ai · 2026-10-02
- ISMIR paper teaches a transformer to play in 12 jazz piano legends' styles — umpedronosapato · 2026-10-02