Reasoning in General Domains without Verifiers

N/A

RLPR: Extrapolating RLVR to General Domains without Verifiers RLPR: E XTRAPOLATING RLVR TO GENERAL DO - MAINS WITHOUT VERIFIERS Tianyu Yu 1†∗ Bo Ji 2† Shouli Wang 4† Shu Yao 5† Zefan Wang 1† Ganqu Cui 1 Lifan Yuan 6 Ning Ding 1 Yuan Yao 2,3‡ Zhiyuan Liu 1‡ Maosong Sun 1 Tat-Seng Chua 2 1…

saved by

• Julia
• Vincent Huang

related reading

• DeepSeek-R1arxiv.org
• [2504.13837] Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?arxiv.org
• [2506.19733] Breaking Barriers: Do Reinforcement Post Training Gains Transfer To Unseen Domains?arxiv.org
• Rubrics as Rewards: Reinforcement Learning Beyond Verifiable Domainsarxiv.org
• LLM Reasoning via One Examplearxiv.org
• Reasoning Models Reason Well, Until They Don'tarxiv.org
• State of RL for reasoning LLMs | A. Weersaweers.de
• You Only Need Minimal RLVR Training: Extrapolating LLMs via Rank-1 Trajectoriesarxiv.org
• The Invisible Leash: Why RLVR May Not Escape Its Originarxiv.org
• [2507.19457] GEPA: Reflective Prompt Evolution Can Outperform Reinforcement Learningarxiv.org
• VRPRM: Process Reward Modeling via Visual Reasoningarxiv.org
• Limit of RLVRlimit-of-rlvr.github.io