MOSCOPT: Mixture-of-Skills Collective Optimization for LLM Agents
Natural language prompts and skills serve as the strategic backbone of LLM-based agents. Recent advances in prompt and skill optimization have achieved notable gains, yet all existing methods optimize a \emph{single} text template---missing the synergy among multiple complementary strategies. We propose MOSCOPT, a text...
Zhen-Yu Zhang, Jiu-Dong Yang
· 0 citations