Application of LLMs to Multi-Robot Path Planning and Task Allocation

2025/07/09 by Ashish Kumar, Kumar, Ashish
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Reinforcement Learning in Robotics #Robot Manipulation and Learning #Robotic Path Planning Algorithms #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2507.07302

openalex publication_date 2025/07/09 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Efficient exploration is a well known problem in deep reinforcement learning and this problem is exacerbated in multi-agent reinforcement learning due the intrinsic complexities of such algorithms. There are several approaches to efficiently explore an environment to learn to solve tasks by multi-agent operating in that environment, of which, the idea of expert exploration is investigated in this work. More specifically, this work investigates the application of large-language models as expert planners for efficient exploration in planning based tasks for multiple agents.

Citations

• Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
• Enabling Intelligent Interactions between an Agent and an LLM: A Reinforcement Learning Approach
• TransfQMix: Transformers for Leveraging the Graph Structure of Multi-Agent Reinforcement Learning Problems
• Offline Robot Reinforcement Learning with Uncertainty-Guided Human Expert Sampling
• PlanBench: An Extensible Benchmark for Evaluating Large Language Models on Planning and Reasoning about Change
• QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning
• Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments
• Emergence of Grounded Compositional Language in Multi-Agent Populations

Related

• Why Solving Multi-agent Path Finding with Large Language Model has not Succeeded Yet
• SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Models
• LLaMAR: Long-Horizon Planning for Multi-Agent Robots in Partially Observable Environments
• Multi-Agent Systems for Robotic Autonomy with LLMs
• LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Planner