3 papers
cs.AI2026
Miner:Mining Intrinsic Mastery for Data-Efficient RL in Large Reasoning Models
Shuyang Jiang, Yuhao Wang, Ya Zhang +2
Current critic-free RL methods for large reasoning models suffer from severe inefficiency when training on positive homogeneous prompts (where all rollouts are correct), resulting…
cs.CL2026
Overthinking Reduction with Decoupled Rewards and Curriculum Data Scheduling
Shuyang Jiang, Yusheng Liao, Ya Zhang +2
While large reasoning models trained with critic-free reinforcement learning and verifiable rewards (RLVR) represent the state-of-the-art, their practical utility is hampered by ``…
cs.LG2025
Automatic Reward Shaping from Multi-Objective Human Heuristics
Yuqing Xie, Jiayu Chen, Wenhao Tang +3
Designing effective reward functions remains a central challenge in reinforcement learning, especially in multi-objective environments. In this work, we propose Multi-Objective Rew…