7 papers
RLVR Datasets and Where to Find Them: Tracing Data Lineage for Better Training Data
Hsiu-Yuan Huang, Weijie Liu, Chenming Tang +5
The proliferation of Reinforcement Learning from Verifiable Rewards (RLVR) datasets has exacerbated provenance collapse due to unclear lineage among existing datasets. To bridge th…
Listwise Policy Optimization: Group-based RLVR as Target-Projection on the LLM Response Simplex
Yun Qu, Qi Wang, Yixiu Mao +11
Reinforcement learning with verifiable rewards (RLVR) has become a standard approach for large language models (LLMs) post-training to incentivize reasoning capacity. Among existin…
Small Generalizable Prompt Predictive Models Can Steer Efficient RL Post-Training of Large Reasoning Models
Yun Qu, Qi Wang, Yixiu Mao +8
Reinforcement learning enhances the reasoning capabilities of large language models but often involves high computational costs due to rollout-intensive optimization. Online prompt…
Debiased Model-based Representations for Sample-efficient Continuous Control
Jiafei Lyu, Zichuan Lin, Scott Fujimoto +5
Model-based representations recently stand out as a promising framework that embeds latent dynamics information into the representations for downstream off-policy actor-critic lear…
Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
Xin Xu, Clive Bai, Kai Yang +7
Large-scale verifiable prompts underpin the success of Reinforcement Learning with Verifiable Rewards (RLVR), but they contain many uninformative examples and are costly to expand…
EntroPIC: Towards Stable Long-Term Training of LLMs via Entropy Stabilization with Proportional-Integral Control
Kai Yang, Xin Xu, Yangkun Chen +5
Long-term training of large language models (LLMs) requires maintaining stable exploration to prevent the model from collapsing into sub-optimal behaviors. Entropy is crucial in th…