Wei Lu

A learned "Token-to-Go" progress meter enables multi-turn RL agents to effectively learn from sparse rewards, boosting performance by up to 7.2 points without increasing training costs.

A directory-aware semantic data management system that tightly integrates semantic and structural access to support structural-context-efficient, evidence-gap-driven multi-round retrieval, and introduces an adaptive escalation strategy that answers from one-round experience-augmented retrieval when the evidence is sufficient, and invokes agentic multi-round retrieval only otherwise.