3 papers
cs.LG2026
GDPO: Mitigating Multi-Reward Conflicts via Group-Dynamic reward-Decoupled Policy Optimization
Haotian Liu, Yihao Liu, Jingwei Ni +11
As LLMs advance, post-training reinforcement learning (RL) increasingly relies on multi-dimensional rewards to cultivate comprehensive capabilities. This shift demands new algorith…
cs.LG2026
CLIPO: Contrastive Learning in Policy Optimization Generalizes RLVR
Sijia Cui, Pengyu Cheng, Jiajun Song +6
Reinforcement Learning with Verifiable Rewards (RLVR) has significantly advanced the reasoning capacity of Large Language Models (LLMs). However, RLVR solely relies on final answer…
cs.LG2025
Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
Zhuo Li, Pengyu Cheng, Zhechao Yu +7
Reward models (RMs) are essential in reinforcement learning from human feedback (RLHF) to align large language models (LLMs) with human values. However, RM training data is commonl…