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
A lightweight orchestration layer makes exploration explicit and programmable while leaving the underlying base agent unchanged, and a key insight is that accumulated discovery history can act as a replay simulator over the realized search space.
Tong Zheng, Xidong Wu, Zheng Zhang et al.· 13 citations
Evaluations demonstrate that RubSE substantially outperforms na\"ive self-evolution in final-round and best-round settings, achieving more stable refinement trajectories and a higher trajectory-level performance ceiling.
Tianyi Xiong, Zhengyuan Yang, Xiaofei Wang et al.· 2 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.