Can One Domain Help Others? A Data-Centric Study on Multi-Domain Reasoning via Reinforcement Learning
"RLVR" 相关文章
The Invisible Leash: Why RLVR May Not Escape Its Origin
Small LLMs Do Not Learn a Generalizable Theory of Mind via Reinforcement Learning
GTR: Guided Thought Reinforcement Prevents Thought Collapse in RL-based VLM Agent Training
StepHint: Multi-level Stepwise Hints Enhance Reinforcement Learning to Reason
性能提升84%-166%！L-Zero仅靠强化学习解锁大模型探索世界的能力 | 已开源
OpenAI路线遭质疑！Meta研究员：根本无法构建超级智能
High-Entropy Token Selection in Reinforcement Learning with Verifiable Rewards (RLVR) Improves Accuracy and Reduces Training Cost for LLMs
Qwen&清华团队颠覆常识：大模型强化学习仅用20%关键token，比用全部token训练还好
奖励是假的，能让Qwen提升25%性能却是真的！
奖励是假的，能让Qwen提升25%性能却是真的
奖励是假的，能让Qwen提升25%性能却是真的！
Incorrect Answers Improve Math Reasoning? Reinforcement Learning with Verifiable Rewards (RLVR) Surprises with Qwen2.5-Math
Reinforcement learning with random rewards actually works with Qwen 2.5
DeepSeek-R1发布100天后：全面复盘推理大模型复现研究及未来！
「推理革命」爆发100天：DeepSeek-R1复现研究全揭秘！
「推理革命」爆发 100 天：DeepSeek-R1 复现研究全揭秘！
强化学习被高估！清华上交：RL不能提升推理能力，新知识得靠蒸馏
强化学习真的会激励 LLM 中超出基本模型的推理能力吗？
R1-Omni开源！全模态模型+RLVR，让各模态作用清晰可见
