3 citations · 4 across the 14 of their papers we have counts for
8 papers · 2 filters
Smaller Models, Better Rejects: Preference Distillation Scaling
Rui Cai, Wenhui Zhu, Xiwen Chen +15
Preference distillation typically treats a teacher response as preferred and the student's own response as rejected. This assumes that self-generated failures are the most informat…
TGRL: Temperature-Grouped Reinforcement Learning for Efficient Exploration in LLMs
Zihan Lin, Xiaohan Wang, Jie Cao +4
Efficient exploration often remains a central bottleneck in reinforcement learning with verifiable rewards (RLVR). Although temperature control and test-time scaling strategies can…
One Step, One Lead: Mitigating Higher-Order Interference in Multi-Domain Reinforcement Learning via Cross-Step Control
Zihan Lin, Xiaohan Wang, Jie Cao +4
Reinforcement learning (RL) across multiple domains can broaden the reasoning capabilities of large language models (LLMs), yet joint training often degrades individual-domain perf…
TREK: Distill to Explore, Reinforce to Refine
Yuanda Xu, Zhengze Zhou, Kayhan Behdin +10
Group Relative Policy Optimization (GRPO) is effective when the current policy already samples useful reasoning trajectories, but it stalls on hard prompts whose correct solution m…
Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training
Yuanda Xu, Hejian Sang, Zhengze Zhou +3
In settings where labeled verifiable training data is the binding constraint, each checked example should be allocated to the model and reward density where it is most informative.…
ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
Zihan Lin, Xiaohan Wang, Jie Cao +6
Reinforcement Learning with Verifiable Rewards (RLVR) enhances reasoning of Large Language Models (LLMs) but usually exhibits limited generation diversity due to the over-incentivi…
Understanding and Mitigating Spurious Signal Amplification in Test-Time Reinforcement Learning for Math Reasoning
Yongcan Yu, Lingxiao He, Jian Liang +5
Test-time reinforcement learning (TTRL) always adapts models at inference time via pseudo-labeling, leaving it vulnerable to spurious optimization signals from label noise. Through…
Overconfident Errors Need Stronger Correction: Asymmetric Confidence Penalties for Reinforcement Learning
Yuanda Xu, Hejian Sang, Zhengze Zhou +2
Reinforcement Learning with Verifiable Rewards (RLVR) has become the leading paradigm for enhancing reasoning in Large Language Models (LLMs). However, standard RLVR algorithms suf…