Multi-Agent Systems2 min read
RoleFlow: Self-Evolving Multi-Role Agentic Collaboration via Structural Adaptation
Large language model (LLM) based multi-agent systems often rely on predefined collaboration structures, limiting their adaptability to evolving task requirements.
By Yi Ge, Pan Wang, Xuehao Cui, Zian Zeng, Xu Hu, Heng Huang, Furong HuangarXiv - cs.AI
Read the full story
Originally published by arXiv - cs.AI on Oct 23, 2026.
Comments
Sign in to join the discussion.