Showing cs.LGShow all
2 papers · 1 filter
cs.LG2026
ACPO: Asymmetric Credit Policy Optimization via Mode-Local Entropy Surrogate
Zijun Xie, Yuyang You, Yongzhi Li +8
Outcome-supervised reinforcement learning scales to verifiable reasoning tasks, but trajectory-level rewards assign the same outcome signal to all sampled tokens, overlooking their…
cs.LG2026
FBOS-RL: Feedback-Driven Bi-Objective Synergistic Reinforcement Learning
Xikai Zhang, Yongzhi Li, Likang Xiao +6
Reinforcement learning has become a cornerstone for aligning and unlocking the reasoning capabilities of large-scale models. At its core, the training loop of GRPO and its variants…