# LLMDR: LLM-Driven Deadlock Detection and Resolution in Multi-Agent Pathfinding

arXiv: https://arxiv.org/abs/2503.00717 · HTML: https://mlsanity.com/paper/2503.00717/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 19 of its 30 references that are in the map.
- First posted on arXiv 2 Mar 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 19 of 19)

- [Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agents](https://mlsanity.com/paper/2201.07207/) (2022)
- [Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory](https://mlsanity.com/paper/2305.17144/) (2023)
- [Multi-Agent Pathfinding: Definitions, Variants, and Benchmarks](https://mlsanity.com/paper/1906.08291/) (2019)
- [SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models](https://mlsanity.com/paper/2309.10062/) (2023)
- [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)
- [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)
- [Mobile Robot Path Planning in Dynamic Environments through Globally Guided Reinforcement Learning](https://mlsanity.com/paper/2005.05420/) (2020)
- [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)
- [MAPPER: Multi-Agent Path Planning with Evolutionary Reinforcement Learning in Mixed Dynamic Environments](https://mlsanity.com/paper/2007.15724/) (2020)
- [Feasibility Study: Moving Non-Homogeneous Teams in Congested Video Game Environments](https://mlsanity.com/paper/1710.01447/) (2017)
- [Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded Yet](https://mlsanity.com/paper/2401.03630/) (2024)
- [Improving Learnt Local MAPF Policies with Heuristic Search](https://mlsanity.com/paper/2403.20300/) (2024)
- [LgTS: Dynamic Task Sampling using LLM-generated sub-goals for Reinforcement Learning Agents](https://mlsanity.com/paper/2310.09454/) (2023)
- [Ensembling Prioritized Hybrid Policies for Multi-agent Pathfinding](https://mlsanity.com/paper/2403.07559/) (2024)
- [SACHA: Soft Actor-Critic with Heuristic-Based Attention for Partially Observable Multi-Agent Path Finding](https://mlsanity.com/paper/2307.02691/) (2023)
- [RDE: A Hybrid Policy Framework for Multi-Agent Path Finding Problem](https://mlsanity.com/paper/2311.01728/) (2023)

## Built on by (most cited first, 1 of 1)

- [Where Paths Collide: A Comprehensive Survey of Classic and Learning-Based Multi-Agent Pathfinding](https://mlsanity.com/paper/2505.19219/) (2025)

## Abstract (arXiv)

Multi-Agent Pathfinding (MAPF) is a core challenge in multi-agent systems. Existing learning-based MAPF methods often struggle with scalability, particularly when addressing complex scenarios that are prone to deadlocks. To address these challenges, we introduce LLMDR (LLM-Driven Deadlock Detection and Resolution), an approach designed to resolve deadlocks and improve the performance of learnt MAPF models. LLMDR integrates the inference capabilities of large language models (LLMs) with learnt MAPF models and prioritized planning, enabling it to detect deadlocks and provide customized resolution strategies. We evaluate LLMDR on standard MAPF benchmark maps with varying agent numbers, measuring its performance when combined with several base models. The results demonstrate that LLMDR improves the performance of learnt MAPF models, particularly in deadlock-prone scenarios, with notable improvements in success rates. These findings show the potential of integrating LLMs to improve the scalability of learning-based MAPF methods. The source code for LLMDR is available at: https://github.com/ssbacc/llmdr-dhc