Compositional Coordination for Multi-Robot Teams with Large Language Models
Not on the map. Why?
Abstract (arXiv)
Multi-robot coordination has traditionally relied on a mission-specific and expert-driven pipeline, where natural language mission descriptions are manually translated by domain experts into mathematical formulation, algorithm design, and executable code. This conventional process is labor-intensive, inaccessible to non-experts, and inflexible to changes in mission requirements. Here, we propose LAN2CB (Language to Collective Behavior), a novel framework that leverages large language models (LLMs) to streamline and generalize the multi-robot coordination pipeline. LAN2CB transforms natural language (NL) mission descriptions into executable Python code for multi-robot systems through two core modules: (1) Mission Analysis, which parses mission descriptions into behavior trees, and (2) Code Generation, which leverages the behavior tree and a structured knowledge base to generate robot control code. We further introduce a dataset of natural language mission descriptions to support development and benchmarking. Experiments in both simulation and real-world environments demonstrate that LAN2CB enables robust and flexible multi-robot coordination from natural language, significantly reducing manual engineering effort and supporting broad generalization across diverse mission types. Website: https://sites.google.com/view/lan-cb
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 33 of its 55 references that are in the map. First posted on arXiv 21 Jul 2025.
Builds on
33 of 55 references.
References · 33
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2020Retrieval-Augmented Generation for Knowledge-Intensive NLP Taskscited by 9,297
- 2022Do As I Can, Not As I Say: Grounding Language in Robotic Affordancescited by 2,348
- 2022Code as Policies: Language Model Programs for Embodied Controlcited by 1,210
- 2024A Survey on Large Language Models for Code Generationcited by 658
- 2022ProgPrompt: Generating Situated Robot Task Plans using Large Language Modelscited by 611
- 2022LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Actioncited by 439
- 2023RoCo: Dialectic Multi-Robot Collaboration with Large Language Modelscited by 172
- 2023Physically Grounded Vision-Language Models for Robotic Manipulationcited by 165
- 2023SMART-LLM: Smart Multi-Agent Robot Task Planning using Large Language Modelscited by 153
- 2023Large Language Models for Robotics: A Surveycited by 133
- 2023AutoTAMP: Autoregressive Task and Motion Planning with LLMs as Translators and Checkerscited by 113
21 more
- 2024Real-Time Anomaly Detection and Reactive Planning with Large Language Modelscited by 68
- 2023VELMA: Verbalization Embodiment of LLM Agents for Vision and Language Navigation in Street Viewcited by 67
- 2024LaMMA-P: Generalizable Multi-Agent Long-Horizon Task Allocation and Planning with LM-Driven PDDL Plannercited by 32
- 2025VideoHallu: Evaluating and Mitigating Multi-modal Hallucinations on Synthetic Video Understandingcited by 32
- 2024PEDANTS: Cheap but Effective and Interpretable Answer Equivalencecited by 31
- 2021Integrated Task Assignment and Path Planning for Capacitated Multi-Agent Pickup and Deliverycited by 30
- 2025Large Language Models for Multi-Robot Systems: A Surveycited by 27
- 2024LiP-LLM: Integrating Linear Programming and dependency graph with Large Language Models for multi-robot task planningcited by 24
- 2025Safety Aware Task Planning via Large Language Models in Roboticscited by 24
- 2023REAL: Resilience and Adaptation using Large Language Models on Autonomous Aerial Robotscited by 19
- 2024SPINE: Online Semantic Planning for Missions with Incomplete Natural Language Specifications in Unstructured Environmentscited by 18
- 2021Beyond Robustness: A Taxonomy of Approaches towards Resilient Multi-Robot Systemscited by 12
- 2025Semantically-Aware Rewards for Open-Ended R1 Training in Free-Form Generationcited by 11
- 2024Improving the TENOR of Labeling: Re-evaluating Topic Models for Content Analysiscited by 10
- 2024Hierarchical LLMs In-the-Loop Optimization for Real-Time Multi-Robot Target Tracking under Unknown Hazardscited by 8
- 2024Can Large Language Models Solve Robot Routing?cited by 6
- 2025GenSwarm: Scalable Multi-Robot Code-Policy Generation and Deployment via Language Modelscited by 4
- 2025AuDeRe: Automated Strategy Decision and Realization in Robot Planning and Control via LLMscited by 4
- 2025Hierarchical Temporal Logic Task and Motion Planning for Multi-Robot Systemscited by 3
- 2025Large Language Models Struggle to Describe the Haystack without Human Help: Human-in-the-loop Evaluation of Topic Modelscited by 2
- 2016Controlling rigid formations of mobile agents under inconsistent measurementscited by 1
Built on by
Citing papers per year: 2026: 3.
3 papers.