mlsanityData to 7 Oct 2026

Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded Yet

arXiv 2401.03630 ↗First posted 8 Jan 2024cs.MA cs.AI cs.CLcited by 22

On the map: LLM agents and tool use → General LLM agent frameworks and benchmarks

Abstract (arXiv)

With the explosive influence caused by the success of large language models (LLM) like ChatGPT and GPT-4, there has been an extensive amount of recent work showing that foundation models can be used to solve a large variety of tasks. However, there is very limited work that shares insights on multi-agent planning. Multi-agent planning is different from other domains by combining the difficulty of multi-agent coordination and planning, and making it hard to leverage external tools to facilitate the reasoning needed. In this paper, we focus on the problem of multi-agent path finding (MAPF), which is also known as multi-robot route planning, and study the performance of solving MAPF with LLMs. We first show the motivating success on an empty room map without obstacles, then the failure to plan on the harder room map and maze map of the standard MAPF benchmark. We present our position on why directly solving MAPF with LLMs has not been successful yet, and we use various experiments to support our hypothesis. Based on our results, we discussed how researchers with different backgrounds could help with this problem from different perspectives.

Key facts. Cited by 22 papers in the map (data through 7 Oct 2026). Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use. Builds on 27 of its 41 references that are in the map. First posted on arXiv 8 Jan 2024.

Builds on

27 of 41 references.

Closest ancestors · 4

Same direction, newest first

  1. 2023Theory of Mind for Multi-Agent Collaboration via Large Language Models16 Oct
  2. 2023LLM-Coordination: Evaluating and Analyzing Multi-agent Coordination Abilities in Large Language Models5 Oct
  3. 2023A Dynamic LLM-Powered Agent Network for Task-Oriented Agent Collaboration3 Oct
  4. 2023Building Cooperative Embodied Agents Modularly with Large Language Models5 Jul

Other references · 23

  1. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,302
  3. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  4. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  5. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  6. 2022Planning with Diffusion for Flexible Behavior Synthesiscited by 1,023
  7. 2023Teaching Large Language Models to Self-Debugcited by 963
  8. 2023Large Language Models as Optimizerscited by 830
  9. 2023LLM+P: Empowering Large Language Models with Optimal Planning Proficiencycited by 496
  10. 2022Complexity-Based Prompting for Multi-Step Reasoningcited by 387
  11. 2023On the Planning Abilities of Large Language Models : A Critical Investigationcited by 308
  12. 2019Multi-Agent Pathfinding: Definitions, Variants, and Benchmarkscited by 197
11 more
  1. 2023The Capacity for Moral Self-Correction in Large Language Modelscited by 171
  2. 2023A Language Agent for Autonomous Drivingcited by 161
  3. 2023Automatic Prompt Augmentation and Selection with Chain-of-Thought from Labeled Datacited by 119
  4. 2023Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?cited by 104
  5. 2018PRIMAL: Pathfinding via Reinforcement and Imitation Multi-Agent Learningcited by 89
  6. 2023Language Conditioned Traffic Generationcited by 86
  7. 2020PRIMAL2: Pathfinding via Reinforcement and Imitation Multi-Agent Learning -- Lifelongcited by 61
  8. 2023Prompt a Robot to Walk with Large Language Modelscited by 44
  9. 2023Learn to Follow: Decentralized Lifelong Multi-agent Pathfinding via Planning and Learningcited by 27
  10. 2023Dialogue Games for Benchmarking Language Understanding: Motivation, Taxonomy, Strategycited by 12
  11. 2019DDM: Fast Near-Optimal Multi-Robot Path Planning using Diversified-Path and Optimal Sub-Problem Solution Database Heuristicscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2024: 8; 2025: 12; 2026: 2.

22 papers.

Sort:

By area:

  1. 2024Dualformer: Controllable Fast and Slow Thinking by Learning with Randomized Reasoning Tracescited by 40
  2. 2025Multi-agent Embodied AI: Advances and Future Directionscited by 36
  3. 2025Large Language Models for Multi-Robot Systems: A Surveycited by 26
  4. 2025RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learningcited by 20
  5. 2024Probabilistically Correct Language-based Multi-Robot Planning using Conformal Predictioncited by 18
  6. 2024RePrompt: Planning by Automatic Prompt Engineering for Large Language Models Agentscited by 15
  7. 2024YOLO-MARL: You Only LLM Once for Multi-Agent Reinforcement Learningcited by 9
  8. 2025LSPO: Length-aware Dynamic Sampling for Policy Optimization in LLM Reasoningcited by 9
  9. 2025SRMT: Shared Memory for Multi-agent Lifelong Pathfindingcited by 8
  10. 2025Iterative Deepening Sampling as Efficient Test-Time Scalingcited by 8
  11. 2024Challenges Faced by Large Language Models in Solving Multi-Agent Flockingcited by 7
  12. 2024Look Further Ahead: Testing the Limits of GPT-4 in Path Planningcited by 7
10 more
  1. 2024Can Large Language Models Solve Robot Routing?cited by 6
  2. 2024Flaming-hot Initiation with Regular Execution Sampling for Large Language Modelscited by 6
  3. 2025Assessing and Enhancing the Robustness of LLM-based Multi-Agent Systems Through Chaos Engineeringcited by 6
  4. 2025GenSwarm: Scalable Multi-Robot Code-Policy Generation and Deployment via Language Modelscited by 4
  5. 2025Where Paths Collide: A Comprehensive Survey of Classic and Learning-Based Multi-Agent Pathfindingcited by 3
  6. 2025LLMDR: LLM-Driven Deadlock Detection and Resolution in Multi-Agent Pathfindingcited by 1
  7. 2025Neural Algorithmic Reasoners informed Large Language Model for Multi-Agent Path Findingcited by 1
  8. 2025Multi-Agent Path Finding via Offline RL and LLM Collaborationcited by 0
  9. 2026ItinBench: Benchmarking Planning Across Multiple Cognitive Dimensions with Large Language Modelscited by 0
  10. 2026HEART: Coordination of Heterogeneous Expert Agents for Physically Grounded Robotic Task Planningcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025MAPF-World: Action World Model for Multi-Agent Path Finding
  2. 2024Query-Efficient Planning with Language Models
  3. 2023Improving Planning with Large Language Models: A Modular Agentic Architecture
  4. 2026Learning to Communicate Locally for Large-Scale Multi-Agent Pathfinding
  5. 2024LLM-A*: Large Language Model Enhanced Incremental Heuristic Search on Path Planning
  6. 2024Multi-Agent Path Finding in Continuous Spaces with Projected Diffusion Models
  7. 2025From Discrete Plans to Real-World Execution: A World-Model-Driven Framework for Execution-Aware Multi-Agent Path Finding
  8. 2025LLMAP: LLM-Assisted Multi-Objective Route Planning with User Preferences