Graph Attention-Guided Search for Dense Multi-Agent Pathfinding

• URL: http://arxiv.org/abs/2510.17382v1
• Date: Mon, 20 Oct 2025 10:19:35 GMT
• Title: Graph Attention-Guided Search for Dense Multi-Agent Pathfinding
• Authors: Rishabh Jain, Keisuke Okumura, Michael Amir, Amanda Prorok,
• Abstract summary: We develop a hybrid framework that integrates a neural MAPF policy with a graph attention scheme into a leading search-based algorithm, LaCAM.<n>Our results demonstrate that, when carefully designed, hybrid search offers a powerful solution for coupled, challenging multi-agent coordination problems.
• Score: 20.439102552204126
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Finding near-optimal solutions for dense multi-agent pathfinding (MAPF) problems in real-time remains challenging even for state-of-the-art planners. To this end, we develop a hybrid framework that integrates a learned heuristic derived from MAGAT, a neural MAPF policy with a graph attention scheme, into a leading search-based algorithm, LaCAM. While prior work has explored learning-guided search in MAPF, such methods have historically underperformed. In contrast, our approach, termed LaGAT, outperforms both purely search-based and purely learning-based methods in dense scenarios. This is achieved through an enhanced MAGAT architecture, a pre-train-then-fine-tune strategy on maps of interest, and a deadlock detection scheme to account for imperfect neural guidance. Our results demonstrate that, when carefully designed, hybrid search offers a powerful solution for tightly coupled, challenging multi-agent coordination problems.

Related papers

• K-Search: LLM Kernel Generation via Co-Evolving Intrinsic World Model [57.440609834690385]
  Existing approaches treat Large Language Models (LLMs) as rapid code generators within evolutionary loops.<n>We propose Search via Co-Evolving World Model and build K-Search based on this method.<n>We evaluate K-Search on diverse, complex kernels FlashInfer, including GQA, MLA, and MoE kernels.
  arXiv  Detail & Related papers  (2026-02-22T11:06:22Z)
• Learning with Local Search MCMC Layers [12.613397606663801]
  We introduce a theoretically-principled approach for learning with inexact solvers.<n>We transform problem-specific neighborhood systems used in local searchs into proposal distributions.<n>We demonstrate our approach on a large-scale dynamic vehicle routing problem with time windows.
  arXiv  Detail & Related papers  (2025-05-20T11:47:42Z)
• POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding [76.67608003501479]
  We introduce POGEMA, a comprehensive set of tools that includes a fast environment for learning, a problem instance generator, and a visualization toolkit.<n>We also introduce and define an evaluation protocol that specifies a range of domain-related metrics, computed based on primary evaluation indicators.<n>The results of this comparison, which involves a variety of state-of-the-art MARL, search-based, and hybrid methods, are presented.
  arXiv  Detail & Related papers  (2024-07-20T16:37:21Z)
• MGCBS: An Optimal and Efficient Algorithm for Solving Multi-Goal Multi-Agent Path Finding Problem [5.580214316179672]
  The MG-MAPF problem requires each agent to visit pre-assigned multiple goal points at least once without conflict. We propose the Multi-Goal Conflict-Based Search (MGCBS), which is based on Decoupling the goal Safe interval visiting order search and the Single-agent pathfinding. Our method can consistently obtain optimal results and execute up to 7 times faster than the state-of-the-art method in our evaluation.
  arXiv  Detail & Related papers  (2024-04-30T12:49:54Z)
• Real-Time Image Segmentation via Hybrid Convolutional-Transformer Architecture Search [51.89707241449435]
  In this paper, we address the challenge of integrating multi-head self-attention into high-resolution representation CNNs efficiently.<n>We develop a multi-target multi-branch supernet method, which fully utilizes the advantages of high-resolution features.<n>We present a series of models via the Hybrid Convolutional-Transformer Architecture Search (HyCTAS) method that searches for the best hybrid combination of light-weight convolution layers and memory-efficient self-attention layers.
  arXiv  Detail & Related papers  (2024-03-15T15:47:54Z)
• Ensembling Prioritized Hybrid Policies for Multi-agent Pathfinding [18.06081009550052]
  Multi-Agent Reinforcement Learning (MARL) based Multi-Agent Path Finding (MAPF) has recently gained attention due to its efficiency and scalability. Several MARL-MAPF methods choose to use communication to enrich the information one agent can perceive. We propose a new method, Ensembling Prioritized Hybrid Policies (EPH)
  arXiv  Detail & Related papers  (2024-03-12T11:47:12Z)
• Decentralized Monte Carlo Tree Search for Partially Observable Multi-agent Pathfinding [49.730902939565986]
  Multi-Agent Pathfinding problem involves finding a set of conflict-free paths for a group of agents confined to a graph. In this study, we focus on the decentralized MAPF setting, where the agents may observe the other agents only locally. We propose a decentralized multi-agent Monte Carlo Tree Search (MCTS) method for MAPF tasks.
  arXiv  Detail & Related papers  (2023-12-26T06:57:22Z)
• Monte-Carlo Tree Search for Multi-Agent Pathfinding: Preliminary Results [60.4817465598352]
  We introduce an original variant of Monte-Carlo Tree Search (MCTS) tailored to multi-agent pathfinding. Specifically, we use individual paths to assist the agents with the the goal-reaching behavior. We also use a dedicated decomposition technique to reduce the branching factor of the tree search procedure.
  arXiv  Detail & Related papers  (2023-07-25T12:33:53Z)
• LaCAM: Search-Based Algorithm for Quick Multi-Agent Pathfinding [5.025654873456756]
  We propose a novel complete algorithm for multi-agent pathfinding (MAPF) called lazy constraints addition search for MAPF (LaCAM) LaCAM uses a two-level search to find solutions quickly, even with hundreds of agents or more. Our experiments reveal that LaCAM is comparable to or outperforms state-of-the-art sub-optimal MAPF algorithms in a variety of scenarios.
  arXiv  Detail & Related papers  (2022-11-24T06:27:18Z)
• Reinforcement Learning for Branch-and-Bound Optimisation using Retrospective Trajectories [72.15369769265398]
  Machine learning has emerged as a promising paradigm for branching. We propose retro branching; a simple yet effective approach to RL for branching. We outperform the current state-of-the-art RL branching algorithm by 3-5x and come within 20% of the best IL method's performance on MILPs with 500 constraints and 1000 variables.
  arXiv  Detail & Related papers  (2022-05-28T06:08:07Z)
• Multi-objective Conflict-based Search Using Safe-interval Path Planning [10.354181009277623]
  We present a new multi-objective conflict-based search (MO-CBS) approach that relies on a novel multi-objective safe interval path planning (MO-SIPP) algorithm for its low-level search. We present extensive numerical results to show that there is an order of magnitude improvement in the average low level search time. We also provide a case study to demonstrate the potential application of the proposed algorithms for construction site planning.
  arXiv  Detail & Related papers  (2021-08-02T09:42:08Z)

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.