# Advancing Learnable Multi-Agent Pathfinding Solvers with Active Fine-Tuning

arXiv: https://arxiv.org/abs/2506.23793 · HTML: https://mlsanity.com/paper/2506.23793/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 33 of its 55 references that are in the map.
- First posted on arXiv 30 Jun 2025.

## Builds on (most cited first, 30 of 33)

- [On the Opportunities and Risks of Foundation Models](https://mlsanity.com/paper/2108.07258/) (2021)
- [OpenVLA: An Open-Source Vision-Language-Action Model](https://mlsanity.com/paper/2406.09246/) (2024)
- [Octo: An Open-Source Generalist Robot Policy](https://mlsanity.com/paper/2405.12213/) (2024)
- [Magentic-One: A Generalist Multi-Agent System for Solving Complex Tasks](https://mlsanity.com/paper/2411.04468/) (2024)
- [ArCHer: Training Language Model Agents via Hierarchical Multi-Turn RL](https://mlsanity.com/paper/2402.19446/) (2024)
- [Foundation Models in Robotics: Applications, Challenges, and the Future](https://mlsanity.com/paper/2312.07843/) (2023)
- [Multi-Agent Pathfinding: Definitions, Variants, and Benchmarks](https://mlsanity.com/paper/1906.08291/) (2019)
- [Foundation Models for Decision Making: Problems, Methods, and Opportunities](https://mlsanity.com/paper/2303.04129/) (2023)
- [Fine-Tuning Large Vision-Language Models as Decision-Making Agents via Reinforcement Learning](https://mlsanity.com/paper/2405.10292/) (2024)
- [Multi-Agent Generative Adversarial Imitation Learning](https://mlsanity.com/paper/1807.09936/) (2018)
- [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)
- [Lifelong Multi-Agent Path Finding in Large-Scale Warehouses](https://mlsanity.com/paper/2005.07371/) (2020)
- [Coordinated Multi-Agent Imitation Learning](https://mlsanity.com/paper/1703.03121/) (2017)
- [Priority Inheritance with Backtracking for Iterative Multi-agent Path Finding](https://mlsanity.com/paper/1901.11282/) (2019)
- [LaCAM: Search-Based Algorithm for Quick Multi-Agent Pathfinding](https://mlsanity.com/paper/2211.13432/) (2022)
- [Amortized Planning with Large-Scale Transformers: A Case Study on Chess](https://mlsanity.com/paper/2402.04494/) (2024)
- [Robot Utility Models: General Policies for Zero-Shot Deployment in New Environments](https://mlsanity.com/paper/2409.05865/) (2024)
- [Message-Aware Graph Attention Networks for Large-Scale Multi-Robot Path Planning](https://mlsanity.com/paper/2011.13219/) (2020)
- [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)
- [Lifelong Path Planning with Kinematic Constraints for Multi-Agent Pickup and Delivery](https://mlsanity.com/paper/1812.06355/) (2018)
- [MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments](https://mlsanity.com/paper/2007.15724/) (2020)
- [POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding](https://mlsanity.com/paper/2407.14931/) (2024)
- [MAPF-GPT: Imitation Learning for Multi-Agent Pathfinding at Scale](https://mlsanity.com/paper/2409.00134/) (2024)
- [Multi-Agent Imitation Learning with Copulas](https://mlsanity.com/paper/2107.04750/) (2021)
- [Conditional Imitation Learning for Multi-Agent Games](https://mlsanity.com/paper/2201.01448/) (2022)
- [Multi-Agent Imitation Learning: Value is Easy, Regret is Hard](https://mlsanity.com/paper/2406.04219/) (2024)

## Built on by (most cited first, 5 of 5)

- [Pairwise is Not Enough: Hypergraph Neural Networks for Multi-Agent Pathfinding](https://mlsanity.com/paper/2602.06733/) (2026)
- [Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding](https://mlsanity.com/paper/2605.07637/) (2026)
- [MAPF-World: Action World Model for Multi-Agent Path Finding](https://mlsanity.com/paper/2508.12087/) (2025)
- [GRACE: A Unified 2D Multi-Robot Path Planning Simulator & Benchmark for Grid, Roadmap, And Continuous Environments](https://mlsanity.com/paper/2603.10858/) (2026)
- [Decentralized Master-Mind: Joint Action Refinement through Iterative Intent Denoising in Multi-Agent Pathfinding](https://mlsanity.com/paper/2609.32019/) (2026)

## Abstract (arXiv)

Multi-agent pathfinding (MAPF) is a common abstraction of multi-robot trajectory planning problems, where multiple homogeneous robots simultaneously move in the shared environment. While solving MAPF optimally has been proven to be NP-hard, scalable, and efficient, solvers are vital for real-world applications like logistics, search-and-rescue, etc. To this end, decentralized suboptimal MAPF solvers that leverage machine learning have come on stage. Building on the success of the recently introduced MAPF-GPT, a pure imitation learning solver, we introduce MAPF-GPT-DDG. This novel approach effectively fine-tunes the pre-trained MAPF model using centralized expert data. Leveraging a novel delta-data generation mechanism, MAPF-GPT-DDG accelerates training while significantly improving performance at test time. Our experiments demonstrate that MAPF-GPT-DDG surpasses all existing learning-based MAPF solvers, including the original MAPF-GPT, regarding solution quality across many testing scenarios. Remarkably, it can work with MAPF instances involving up to 1 million agents in a single environment, setting a new milestone for scalability in MAPF domains.