Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems?

This is experimental HTML to improve accessibility. We invite you to report rendering errors. Use Alt+Y to toggle on accessible reporting links and Alt+Shift+Y to toggle off. Learn more about this project and help improve conversions. A flurry of recent work has demonstrated that pre-trained large language models (LLMs) can be effective task planners for a variety of single-robot tasks. The planning performance of LLMs is significantly improved via prompting techniques, such as in-context learning or re-prompting with state feedback, placing new importance on the token budget for the context window. An under-explored but natural next direction is to investigate LLMs as multi-robot task planners. However, long-horizon, heterogeneous multi-robot planning introduces new challenges of coordination while also pushing up against the limits of context window length. It is therefore critical to find token-efficient LLM planning frameworks that are also able to reason about the complexities of

Scalable Multi-Robot Collaboration with Large Language Models: Centralized or Decentralized Systems? Yongchao Chen 1 , 2 1 2 {}^{1,2} start_FLOATSUPERSCRIPT 1 , 2 end_FLOATSUPERSCRIPT , Jacob Arkin 1 1 {}^{1} start_FLOATSUPERSCRIPT 1 end_FLOATSUPERSCRIPT , Yang Zhang 3 3 {}^{3} start_FLOATSUPERSCRIPT 3 end_FLOATSUPERSCRIPT , Nicholas Roy 1 1 {}^{1} start_FLOATSUPERSCRIPT 1 end_FLOATSUPERSCRIPT , and Chuchu Fan 1 1 {}^{1} start_FLOATSUPERSCRIPT 1 end_FLOATSUPERSCRIPT 1 1 {}^{1} start_FLOATSUPERSCRIPT 1 end_FLOATSUPERSCRIPT Massachusetts Institute of Technology. jarkin@mit.edu, nickroy@csail.mit

related reading

• Emergence of Human to Robot Transfer in Vision-Language-Action Modelspi.website
• [2510.13786] The Art of Scaling Reinforcement Learning Compute for LLMsarxiv.org
• How Claude Performs on Robotics Tasks \ Anthropicanthropic.com
• Language Models can Solve Computer Tasksarxiv.org
• [2201.07207] Language Models as Zero-Shot Planners: Extracting Actionable Knowledge for Embodied Agentsarxiv.org
• Theory of Mind for Multi-Agent Collaboration via Large Language Modelsarxiv.org
• A Careful Examination of Large Behavior Models for Multitask Dexterous Manipulationtoyotaresearchinstitute.github.io
• AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkersarxiv.org
• [2410.00079] Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interfacearxiv.org
• [2603.21972] Demystifying Reinforcement Learning for Long-Horizon Tool-Using Agents: A Comprehensive Recipearxiv.org
• Are Emergent Abilities in Large Language Models just In-Context Learning?arxiv.org
• [2304.13343] Unleashing Infinite-Length Input Capacity for Large-scale Language Models with Self-Controlled Memory Systemarxiv.org