method · first seen 12 Oct 2026
test-time reinforcement learning
Also: TTRL, test-time RL
Adapting a language model with reinforcement learning on unlabeled test problems using pseudo-labels from sampled responses.
Mentions per week
PapersCodeDiscussion
Rank 137 on 11 Nov 2026 · 7 mentions in 28 days · 5 independent groups · papers · first seen 4 weeks ago · acceleration +1.66
Earliest sources
- SelectTTRL: Representation-Guided Data Selection for Efficient Test-Time Reinforcement LearningPapers · 12 Oct 2026 · Yi Li, Linan Yue, Weibo Gao
- PaceReasoner: Label-Free Learning to Answer Briefly from Long ReasoningPapers · 13 Oct 2026 · Changguo Jia, Zhiyou Xiao, Xinbei Ma, Geng Chen, Weiming Zhang, Yiming Xu, Tianq…
- MS-TTRL: Breaking the Frequency Conflict in Multiple-Solution Test-Time Reinforcement LearningPapers · 23 Oct 2026 · Zhixia Zhang, Binqian Xu, Huaiyang Wang, Yikun Ban, Dianbo Liu
- Timbre: Reliability-aware harmonic consensus for label-free multimodal test-time rexinforcement learningPapers · 29 Oct 2026 · Haotian Lyu, Haoyu Wang, Ru Wang, Feng Ji, Ziwen Li, Jiaxian Guo, Mingming Gong
- Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating TransferPapers · 30 Oct 2026 · Minju Gwak, Alan Ritter
- When Does Exploration Prevent Collapse? Three Regimes and the Path of the Reward in Self-Consistency TrainingPapers · 31 Oct 2026 · Jaeho Hwang, Uiwon Hwang
Latest sources
- TRUER: Test-Time Reward Correction Using an Error-Aware Rectifier for Reinforcement LearningPapers · 10 Nov 2026 · Mingxiang Shen, Jinhao Li, Jiaming Xu, Yibo Han, Guohao Dai, Yijia Zhang, Ningyi…
- The Race Is Decided Early! A Kernel Law Predicts Lock-In in Majority-Vote Test-Time RLPapers · 8 Nov 2026 · Jaeho Hwang, Sehong Park, Daejin Choi, Uiwon Hwang
- On the Reliability of Majority-Vote Pseudo-Labels in Test-Time Reinforcement LearningPapers · 6 Nov 2026 · Haoyu Wang, Ru Wang, Yuanyuan Wang, Jiaxian Guo, Mingming Gong
- When Does Exploration Prevent Collapse? Three Regimes and the Path of the Reward in Self-Consistency TrainingPapers · 31 Oct 2026 · Jaeho Hwang, Uiwon Hwang
- Self-Improvement with Auxiliary Rewards: Learning from Verified Traces and Evaluating TransferPapers · 30 Oct 2026 · Minju Gwak, Alan Ritter
- Timbre: Reliability-aware harmonic consensus for label-free multimodal test-time rexinforcement learningPapers · 29 Oct 2026 · Haotian Lyu, Haoyu Wang, Ru Wang, Feng Ji, Ziwen Li, Jiaxian Guo, Mingming Gong
- MS-TTRL: Breaking the Frequency Conflict in Multiple-Solution Test-Time Reinforcement LearningPapers · 23 Oct 2026 · Zhixia Zhang, Binqian Xu, Huaiyang Wang, Yikun Ban, Dianbo Liu
- PaceReasoner: Label-Free Learning to Answer Briefly from Long ReasoningPapers · 13 Oct 2026 · Changguo Jia, Zhiyou Xiao, Xinbei Ma, Geng Chen, Weiming Zhang, Yiming Xu, Tianq…
- SelectTTRL: Representation-Guided Data Selection for Efficient Test-Time Reinforcement LearningPapers · 12 Oct 2026 · Yi Li, Linan Yue, Weibo Gao