Multi-Agent Systems for Robotic Autonomy with LLMs
This work addresses the challenge of improving efficiency and accessibility in robotic system development for research and industrial applications, representing an incremental advancement by integrating existing LLMs into a multi-agent framework.
The paper tackles the problem of robotic system development by proposing a multi-agent framework with LLMs for task analysis, mechanical design, and path generation, resulting in a system that can design feasible robots with control strategies, as demonstrated in experiments with GPT and DeepSeek models.
Since the advent of Large Language Models (LLMs), various research based on such models have maintained significant academic attention and impact, especially in AI and robotics. In this paper, we propose a multi-agent framework with LLMs to construct an integrated system for robotic task analysis, mechanical design, and path generation. The framework includes three core agents: Task Analyst, Robot Designer, and Reinforcement Learning Designer. Outputs are formatted as multimodal results, such as code files or technical reports, for stronger understandability and usability. To evaluate generalizability comparatively, we conducted experiments with models from both GPT and DeepSeek. Results demonstrate that the proposed system can design feasible robots with control strategies when appropriate task inputs are provided, exhibiting substantial potential for enhancing the efficiency and accessibility of robotic system development in research and industrial applications.