Mengkang Hu

LLM agents can enhance training-data strategies in over half of their attempts, but their inconsistency reveals critical limitations in recursive self-improvement.

LLM agents struggle to maintain performance in multi-day collaborative tasks, dropping significantly after just one environmental update, revealing a critical gap in adaptation to evolving real-world conditions.

Forget trajectory-level rollouts: MuSEAgent learns faster and reasons better by distilling past interactions into reusable, state-aware decision experiences.