5 papers · 1 filter
VRPO: Rethinking Value Modeling for Robust RL under Noisy Supervision in LLM Post-Training
Dingwei Zhu, Shihan Dou, Zhiheng Xi +16
Reinforcement Learning (RL) in real-world environments often suffers from ambiguous or incomplete reward supervision, which undermines policy stability and generalization. Such noi…
DFPO: Scaling Value Modeling via Distributional Flow towards Robust and Generalizable LLM Post-Training
Dingwei Zhu, Zhiheng Xi, Shihan Dou +17
Training reinforcement learning (RL) systems in real-world environments remains challenging due to noisy supervision and poor out-of-domain (OOD) generalization, especially in LLM…
DVPO: Distributional Value Modeling-based Policy Optimization for LLM Post-Training
Dingwei Zhu, Zhiheng Xi, Shihan Dou +15
Reinforcement learning (RL) has shown strong performance in LLM post-training, but real-world deployment often involves noisy or incomplete supervision. In such settings, complex a…
AgentGym-RL: Training LLM Agents for Long-Horizon Decision Making through Multi-Turn Reinforcement Learning
Zhiheng Xi, Jixuan Huang, Chenyang Liao +20
Developing autonomous LLM agents capable of making a series of intelligent decisions to solve complex, real-world tasks is a fast-evolving frontier. Like human cognitive developmen…
MetaRM: Shifted Distributions Alignment via Meta-Learning
Shihan Dou, Yan Liu, Enyu Zhou +9
The success of Reinforcement Learning from Human Feedback (RLHF) in language model alignment is critically dependent on the capability of the reward model (RM). However, as the tra…