Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
Claw-R1: A Step-Level Data Middleware System for Agentic Reinforcement Learning
Daoyu Wang, Mingyue Cheng, Qingchuan Li +3
Agentic reinforcement learning (RL) has become an important post-training paradigm for turning LLMs from static chatbots into interactive agents, giving rise to representative appl…
cs.LG2026
SocraticPO: Policy Optimization via Interactive Guidance
Zirui Liu, Tingyue Pan, Jie Ouyang +8
Reinforcement learning (RL) for large language models usually supervises reasoning with scalar outcome rewards, such as binary correctness. Such rewards provide an optimization dir…