MAPF-World: Action World Model for Multi-Agent Path Finding

• URL: http://arxiv.org/abs/2508.12087v2
• Date: Sun, 07 Sep 2025 04:05:16 GMT
• Title: MAPF-World: Action World Model for Multi-Agent Path Finding
• Authors: Zhanjiang Yang, Yang Shen, Yueming Li, Meng Li, Lijun Sun,
• Abstract summary: Multi-agent path finding (MAPF) is the problem of planning conflict-free paths from the designated start locations to goal positions for multiple agents.<n>Recent decentralized learnable solvers have shown great promise for large-scale MAPF.<n>We propose MAPF-World, an autoregressive action world model for MAPF that unifies situation understanding and action generation.
• Score: 17.847921829680576
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Multi-agent path finding (MAPF) is the problem of planning conflict-free paths from the designated start locations to goal positions for multiple agents. It underlies a variety of real-world tasks, including multi-robot coordination, robot-assisted logistics, and social navigation. Recent decentralized learnable solvers have shown great promise for large-scale MAPF, especially when leveraging foundation models and large datasets. However, these agents are reactive policy models and exhibit limited modeling of environmental temporal dynamics and inter-agent dependencies, resulting in performance degradation in complex, long-term planning scenarios. To address these limitations, we propose MAPF-World, an autoregressive action world model for MAPF that unifies situation understanding and action generation, guiding decisions beyond immediate local observations. It improves situational awareness by explicitly modeling environmental dynamics, including spatial features and temporal dependencies, through future state and actions prediction. By incorporating these predicted futures, MAPF-World enables more informed, coordinated, and far-sighted decision-making, especially in complex multi-agent settings. Furthermore, we augment MAPF benchmarks by introducing an automatic map generator grounded in real-world scenarios, capturing practical map layouts for training and evaluating MAPF solvers. Extensive experiments demonstrate that MAPF-World outperforms state-of-the-art learnable solvers, showcasing superior zero-shot generalization to out-of-distribution cases. Notably, MAPF-World is trained with a 96.5% smaller model size and 92% reduced data.

Related papers

• Bridging Planning and Execution: Multi-Agent Path Finding Under Real-World Deadlines [9.228609005424348]
  We propose REMAP, an execution-informed MAPF planning framework for time-sensitive applications.<n>Our framework integrates the proposed ExecTimeNet to accurately estimate execution time based on planned paths.<n>Experiments show that REMAP achieves up to 20% improvement in solution quality over baseline methods.
  arXiv  Detail & Related papers  (2025-11-26T20:08:52Z)
• ExoPredicator: Learning Abstract Models of Dynamic Worlds for Robot Planning [77.49815848173613]
  We propose a framework for abstract world models that jointly learns symbolic state representations and causal processes for both endogenous actions and mechanisms.<n>Across five simulated tabletop robotics environments, the learned models enable fast planning that generalizes to held-out tasks with more objects and more complex goals, outperforming a range of baselines.
  arXiv  Detail & Related papers  (2025-09-30T13:44:34Z)
• Sequence Pathfinder for Multi-Agent Pickup and Delivery in the Warehouse [10.576983033957953]
  Multi-Agent Pickup and Delivery (MAPD) is a challenging extension of Multi-Agent Path Finding (MAPF)<n> Communication learning can alleviate the lack of global information but introduce high computational complexity due to point-to-point communication.<n>We propose the Sequential Pathfinder (SePar) to achieve implicit information exchange, reducing decision-making complexity from exponential to linear.
  arXiv  Detail & Related papers  (2025-09-28T09:48:13Z)
• Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-Tuning [46.35418789518417]
  Multi-agent pathfinding (MAPF) is a common abstraction of multi-robot trajectory planning problems.<n>We introduce MAPF-GPT-DDG, a decentralized suboptimal MAPF solvers that leverage machine learning.<n>Our experiments demonstrate that MAPF-GPT-DDG surpasses all existing learning-based MAPF solvers.
  arXiv  Detail & Related papers  (2025-06-30T12:34:31Z)
• WorldPrediction: A Benchmark for High-level World Modeling and Long-horizon Procedural Planning [52.36434784963598]
  We introduce WorldPrediction, a video-based benchmark for evaluating world modeling and procedural planning capabilities of different AI models.<n>We show that current frontier models barely achieve 57% accuracy on WorldPrediction-WM and 38% on WorldPrediction-PP whereas humans are able to solve both tasks perfectly.
  arXiv  Detail & Related papers  (2025-06-04T18:22:40Z)
• Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective [54.77404771454794]
  We develop a flexible and robust world model for Multi-Agent Reinforcement Learning (MARL) using diffusion models.<n>Our method, Diffusion-Inspired Multi-Agent world model (DIMA), achieves state-of-the-art performance across multiple multi-agent control benchmarks.
  arXiv  Detail & Related papers  (2025-05-27T09:11:38Z)
• RAILGUN: A Unified Convolutional Policy for Multi-Agent Path Finding Across Different Environments and Tasks [17.17370365888357]
  Multi-Agent Path Finding (MAPF) is crucial for applications ranging from aerial swarms to warehouse automation.<n>We have developed the first centralized learning-based policy for MAPF problem called RAILGUN.<n>By leveraging a CNN-based architecture, RAILGUN can generalize across different maps and handle any number of agents.
  arXiv  Detail & Related papers  (2025-03-04T20:35:20Z)
• MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale [46.35418789518417]
  Multi-agent pathfinding (MAPF) is a problem that generally requires finding collision-free paths for multiple agents in a shared environment.<n>Recently, learning-based approaches to MAPF have gained attention, particularly those leveraging deep reinforcement learning.<n>We show that MAPF-GPT notably outperforms the current best-performing learnable MAPF solvers on a diverse range of problem instances.
  arXiv  Detail & Related papers  (2024-08-29T12:55:10Z)
• Scalable Mechanism Design for Multi-Agent Path Finding [87.40027406028425]
  Multi-Agent Path Finding (MAPF) involves determining paths for multiple agents to travel simultaneously and collision-free through a shared area toward given goal locations. Finding an optimal solution is often computationally infeasible, making the use of approximate, suboptimal algorithms essential. We introduce the problem of scalable mechanism design for MAPF and propose three strategyproof mechanisms, two of which even use approximate MAPF algorithms.
  arXiv  Detail & Related papers  (2024-01-30T14:26:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.