2 papers
cs.CL2026
Write, Execute, Refine: From Skill Follower to Skill Optimizer via Reinforcement Learning from Execution Feedback
Kang Peng, Zhiwei Zhang, Yichen Zhang +7
Expert-written natural language skills can improve tool-using agents, yet agent-authored skills perform 8--11 points worse than using no skill. While inference-time loops can repai…
stat.ML2026
Self-Normalized Inference for Constant-Stepsize Temporal-Difference Learning under Markovian Sampling
Min Zeng, Yichen Zhang, Xiaofeng Shao
Constant-stepsize temporal-difference (TD) learning is attractive for policy evaluation, but inference from a single Markov trajectory must account for serial dependence and a step…