Multi-Agent Collaboration via Evolving Orchestration
This work addresses scalability and efficiency issues in complex problem-solving for multi-agent LLM systems, representing an incremental improvement over existing methods.
The paper tackles the problem of static organizational structures in multi-agent LLM collaboration, which leads to inefficiencies as task complexity grows, by proposing a puppeteer-style paradigm where a centralized orchestrator dynamically directs agents via reinforcement learning, achieving superior performance with reduced computational costs in experiments.
Large language models (LLMs) have achieved remarkable results across diverse downstream tasks, but their monolithic nature restricts scalability and efficiency in complex problem-solving. While recent research explores multi-agent collaboration among LLMs, most approaches rely on static organizational structures that struggle to adapt as task complexity and agent numbers grow, resulting in coordination overhead and inefficiencies. To this end, we propose a puppeteer-style paradigm for LLM-based multi-agent collaboration, where a centralized orchestrator ("puppeteer") dynamically directs agents ("puppets") in response to evolving task states. This orchestrator is trained via reinforcement learning to adaptively sequence and prioritize agents, enabling flexible and evolvable collective reasoning. Experiments on closed- and open-domain scenarios show that this method achieves superior performance with reduced computational costs. Analyses further reveal that the key improvements consistently stem from the emergence of more compact, cyclic reasoning structures under the orchestrator's evolution. Our code is available at https://github.com/OpenBMB/ChatDev/tree/puppeteer.