Online automatic code generation for robot swarms: LLMs and self-organizing hierarchy

2025/10/06 by Weixu Zhu, Marco Dorigo, Zhu, Weixu +3
Computer Science · Engineering · #Artificial Intelligence (cs.AI) #Evolutionary Algorithms and Applications #FOS: Computer and information sciences #Modular Robots and Swarm Intelligence #Multiagent Systems (cs.MA) #Robotics (cs.RO)

paper · pdf · doi:10.48550/arxiv.2510.04774

openalex publication_date 2025/10/06 · openalex created_date 2025/10/09 · openalex updated_date 2026/07/28

Abstract

Our recently introduced self-organizing nervous system (SoNS) provides robot swarms with 1) ease of behavior design and 2) global estimation of the swarm configuration and its collective environment, facilitating the implementation of online automatic code generation for robot swarms. In a demonstration with 6 real robots and simulation trials with >30 robots, we show that when a SoNS-enhanced robot swarm gets stuck, it can automatically solicit and run code generated by an external LLM on the fly, completing its mission with an 85% success rate.

Citations

• DeepSeek-R1 incentivizes reasoning in LLMs through reinforcement learning
• LLM2Swarm: Robot Swarms that Responsively Reason, Plan, and Collaborate through LLMs
• Self-organizing Nervous Systems for Robot Swarms

Cited by

• TACOS: Task Agnostic COordinator of a multi-drone System

Related

• Self-organizing Nervous Systems for Robot Swarms
• Buzz: An Extensible Programming Language for Self-Organizing Heterogeneous Robot Swarms
• LLM2Swarm: Robot Swarms that Responsively Reason, Plan, and Collaborate through LLMs
• Swarmrobot.org - Open-hardware Microrobotic Project for Large-scale Artificial Swarms
• LLM-Powered Swarms: A New Frontier or a Conceptual Stretch?