TTRL: Test-Time Reinforcement Learning.
Release time:2026-08-26
Hits:
- Journal:
- NeurIPS, 2025
- Abstract:
- Yuxin Zuo, Kaiyan Zhang, Li Sheng, Shang Qu, Ganqu Cui, Xuekai Zhu, Haozhan Li, yuchen zhang, Xinwei Long, Ermo Hua, Biqing Qi, Youbang Sun, Zhiyuan Ma, Lifan Yuan, Ning Ding, Bowen Zhou†
- Note:
- RL Reasoning Enabling LLMs to learn and improve reasoning strategies at test time without additional training data
- Translation or Not:
- no
- Links to published journals:
- https://proceedings.neurips.cc/paper_files/paper/2025/hash/be690ea16f005c174f6c4102a5970e67-Abstract-Conference.html