Multi-Agent Collaboration via Cross-Team Orchestration
This addresses the problem of suboptimal or inefficient outcomes in multi-agent collaboration for software development and other domains, representing an incremental improvement over existing methods.
The paper tackles the limitation of single-outcome development chains in LLM-driven multi-agent teams by introducing Cross-Team Orchestration (Croto), a scalable framework that enables multiple teams to propose diverse solutions and collaborate, resulting in a notable increase in software quality compared to state-of-the-art baselines.
Large Language Models (LLMs) have significantly impacted various domains, especially through organized LLM-driven autonomous agents. A representative scenario is in software development, where agents can collaborate in a team like humans, following predefined phases to complete sub-tasks sequentially. However, for an agent team, each phase yields only one possible outcome. This results in the completion of only one development chain, thereby losing the opportunity to explore multiple potential decision paths within the solution space. Consequently leading to suboptimal results or extensive trial and error. To address this, we introduce Cross-Team Orchestration (Croto), a scalable multi-team framework that enables orchestrated teams to jointly propose various task-oriented solutions and interact with their insights in a self-independence while cross-team collaboration environment for superior solutions generation. Experiments reveal a notable increase in software quality compared to state-of-the-art baselines. We further tested our framework on story generation tasks, which demonstrated a promising generalization ability of our framework in other domains. The code and data is available at https://github.com/OpenBMB/ChatDev/tree/macnet