Preprint
Oct 2026
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. Although recent approaches enable dynamic orchestration, trajectory-level rewards they apply assign one outcome to each decision, ofen struggling to identify...
Yi-Rou Ge, Pan Wang, Xue-Hao Cui et al.
· 0 citations