AI RESEARCH
MAS-ZERO: Designing Multi-Agent Systems with Zero Supervision
arXiv CS.LG
•
ArXi:2505.14996v4 Announce Type: replace-cross Multi-agent systems (MAS) leveraging the impressive capabilities of Large Language Models (LLMs) hold significant potential for tackling complex tasks. However, most current MAS depend on manually designed agent roles and communication protocols. These manual designs often fail to align with the underlying LLMs' strengths and struggle to adapt to novel tasks.