Verifier-Mediated Multi-LLM Coordination for Multi-Robot Path Planning

Abstract:Foundation models are increasingly used for high-level multi-robot task planning, yet independently generated symbolic plans can become jointly infeasible after geometric grounding because of shared spatial and temporal constraints. We study execution-aware coordination of large-language-model (LLM) planners for multi-robot navigation. We compare a centralized architecture, in which one LLM jointly reasons over the robot team, with a decentralized multi-LLM architecture in which each robot independently proposes a task plan. A geometric verifier grounds the candidate plans into robot trajectories, detects predicted inter-robot conflicts, and converts conflict information into structured feedback for targeted replanning. This verifier-mediated architecture separates semantic task reasoning from execution-level feasibility while enabling iterative coordination among LLM planners. Experiments in CARLA and on Crazyflie aerial robots evaluate coordination performance as task complexity increases and characterize the trade-offs between centralized reasoning, decentralized verifier-mediated coordination, and physical executability.

Robotics (cs.RO); Systems and Control (eess.SY)

arXiv:2610.12761 [cs.RO]

(or arXiv:2610.12761v1 [cs.RO] for this version)

https://doi.org/10.48550/arXiv.2610.12761 Focus to learn more arXiv-issued DOI via DataCite (pending registration)

https://openreview.net/group?id=IEEE.org/IROS/2026/Workshop/FM-MRS#tab-recent-activity; https://zhourobotics.github.io/fm-mrs/

arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.

Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.

Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.