2 citations · 2 across the 6 of their papers we have counts for
Showing cs.LGShow all
3 papers · 1 filter
cs.LG2026
T2SPO: Trajectory-to-Step Policy Optimization for Agentic Reinforcement Learning
Bo-Wen Zhang, Junwei He, Maoqi Liu +6
Reinforcement learning enables large language model (LLM) agents to learn multi-step behaviors through interaction with their environments. However, rewards in many interactive tas…
cs.LG2026
Scoring Higher, Answering Worse: Mitigating Reward Hacking in Rubric-Based RL via Protocol-Level Rubrics
Maoqi Liu, Junwei He, Bowen Zhang +5
Rubric-based reinforcement learning (Rubric-RL) trains language models where no verifier exists. A judge checks each criterion of a rubric, and the verdicts are aggregated into a r…
cs.LG2026
Rethinking Data Curation in LLM Training: Online Reweighting Offers Better Generalization than Offline Methods
Wanru Zhao, Yihong Chen, Yuzhi Tang +6
Data curation is a critical yet under-explored area in large language model (LLM) training. Existing methods, such as data selection and mixing, operate in an offline paradigm, det…