AI RESEARCH
An Empirical Study of Multi-Agent Collaboration for Automated Research
arXiv CS.AI
•
ArXi:2603.29632v1 Announce Type: cross As AI agents evolve, the community is rapidly shifting from single Large Language Models (LLMs) to Multi-Agent Systems (MAS) to overcome cognitive bottlenecks in automated research. However, the optimal multi-agent coordination framework for these autonomous agents remains largely unexplored. In this paper, we present a systematic empirical study investigating the comparative efficacy of distinct multi-agent structures for automated machine learning optimization.