# Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding

arXiv: https://arxiv.org/abs/2602.06733 · HTML: https://mlsanity.com/paper/2602.06733/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 27 of its 46 references that are in the map.
- First posted on arXiv 6 Feb 2026.

## Builds on (most cited first, 27 of 27)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [A Unified Approach to Interpreting Model Predictions](https://mlsanity.com/paper/1705.07874/) (2017)
- [Safe, Multi-Agent, Reinforcement Learning for Autonomous Driving](https://mlsanity.com/paper/1610.03295/) (2016)
- [Hypergraph Convolution and Hypergraph Attention](https://mlsanity.com/paper/1901.08150/) (2019)
- [Multi-Agent Pathfinding: Definitions, Variants, and Benchmarks](https://mlsanity.com/paper/1906.08291/) (2019)
- [GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning](https://mlsanity.com/paper/2204.08770/) (2022)
- [Be Confident! Towards Trustworthy Graph Neural Networks via Confidence Calibration](https://mlsanity.com/paper/2109.14285/) (2021)
- [PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learning](https://mlsanity.com/paper/1809.03531/) (2018)
- [Graph Neural Networks for Decentralized Multi-Robot Path Planning](https://mlsanity.com/paper/1912.06095/) (2019)
- [Relational Graph Attention Networks](https://mlsanity.com/paper/1904.05811/) (2019)
- [Priority Inheritance with Backtracking for Iterative Multi-agent Path Finding](https://mlsanity.com/paper/1901.11282/) (2019)
- [Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning](https://mlsanity.com/paper/2011.13219/) (2020)
- [What Makes Graph Neural Networks Miscalibrated?](https://mlsanity.com/paper/2210.06391/) (2022)
- [Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learning](https://mlsanity.com/paper/2005.05420/) (2020)
- [SCRIMP: Scalable Communication for Reinforcement- and Imitation-Learning-Based Multi-Agent Pathfinding](https://mlsanity.com/paper/2303.00605/) (2023)
- [Learning Selective Communication for Multi-Agent Path Finding](https://mlsanity.com/paper/2109.05413/) (2021)
- [POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding](https://mlsanity.com/paper/2407.14931/) (2024)
- [Multi-Agent Dynamic Relational Reasoning for Social Robot Navigation](https://mlsanity.com/paper/2401.12275/) (2024)
- [MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale](https://mlsanity.com/paper/2409.00134/) (2024)
- [Improving Learnt Local MAPF Policies with Heuristic Search](https://mlsanity.com/paper/2403.20300/) (2024)
- [MAGNNETO: A Graph Neural Network-based Multi-Agent system for Traffic Engineering](https://mlsanity.com/paper/2303.18157/) (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)
- [Refined Hardness of Distance-Optimal Multi-Agent Path Finding](https://mlsanity.com/paper/2203.07416/) (2022)
- [RAILGUN: A Unified Convolutional Policy for Multi-Agent Path Finding Across Different Environments and Tasks](https://mlsanity.com/paper/2503.02992/) (2025)
- [Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-Tuning](https://mlsanity.com/paper/2506.23793/) (2025)
- [DeepFleet: Multi-Agent Foundation Models for Mobile Robots](https://mlsanity.com/paper/2508.08574/) (2025)
- [SDHN: Skewness-Driven Hypergraph Networks for Enhanced Localized Multi-Robot Coordination](https://mlsanity.com/paper/2504.06684/) (2025)

## Built on by (most cited first, 4 of 4)

- [Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding](https://mlsanity.com/paper/2605.07637/) (2026)
- [Discrete Diffusion for Complex and Congested Multi-Agent Path Finding with Sparse Social Attention](https://mlsanity.com/paper/2605.13296/) (2026)
- [Decentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding](https://mlsanity.com/paper/2609.32019/) (2026)
- [PANDA: Prior-guided Attentional Dual-path Architecture](https://mlsanity.com/paper/2610.13635/) (2026)

## Abstract (arXiv)

Multi-Agent Path Finding (MAPF) is a representative multi-agent coordination problem, where multiple agents are required to navigate to their respective goals without collisions. Solving MAPF optimally is known to be NP-hard, leading to the adoption of learning-based approaches to alleviate the online computational burden. Prevailing approaches, such as Graph Neural Networks (GNNs), are typically constrained to pairwise message passing between agents. However, this limitation leads to suboptimal behaviours and critical issues, such as attention dilution, particularly in dense environments where group (i.e. beyond just two agents) coordination is most critical. Despite the importance of such higher-order interactions, existing approaches have not been able to fully explore them. To address this representational bottleneck, we introduce HMAGAT (Hypergraph Multi-Agent Attention Network), a novel architecture that leverages attentional mechanisms over directed hypergraphs to explicitly capture group dynamics. Empirically, HMAGAT establishes a new state-of-the-art among learning-based MAPF solvers: e.g., despite having just 1M parameters and being trained on 100× less data, it outperforms the current SoTA 85M parameter model. Through detailed analysis of HMAGAT's attention values, we demonstrate how hypergraph representations mitigate the attention dilution inherent in GNNs and capture complex interactions where pairwise methods fail. Our results illustrate that appropriate inductive biases are often more critical than the training data size or sheer parameter count for multi-agent problems.