method · first seen 4 Oct 2026
reinforcement learning with verifiable rewards
Also: GDPO, RLVF, RLVR, verifier RL, verifiable rewards, outcome reinforcement learning, verifier-guided reinforcement learning, verifiable reward reinforcement learning
Post-training of language models using rule-checkable rewards such as final-answer correctness instead of learned reward models.
Reinforcement learning with verifiable rewards (RLVR) post-trains language models against rewards that a rule or program can check, such as a correct final math answer or passing tests, rather than a learned reward model. The sources treat it as standard infrastructure. Papers propose refinements: token-level credit assignment for multimodal reasoning, negative-only optimization when verifiers can only falsify answers, Pareto rankings across multiple verifiers, and self-distillation framed through RLVR advantages. Others apply it to streaming speech recognition, paper reviewing and collider-physics tasks. Small repos use it as a tag for observability and distillation pipelines, and a Tsinghua group released code for a listwise policy optimization method.
RLVR is already the default recipe for reasoning post-training, so the apparent rise here mostly reflects how many papers now use it as a baseline. The more interesting work is at the edges: what to do when verification is partial, noisy or one-sided.
Analyst note (established), 17 Nov 2026.
Mentions per week
PapersCodeDiscussion
Rank 59 on 14 Nov 2026 · 114 mentions in 28 days · 113 independent groups · papers → discussion → code · first seen 6 weeks ago · acceleration -0.06
Earliest sources
- CURIO: Curiosity-Driven Test-Time Learning for Open-Ended DiscoveryPapers · 4 Oct 2026 · Tao Feng, Fangxu Yu, Zijie Lei, Jiaru Zou, Changjiang Jiang, Yi Yan, Jiaxuan You…
- Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement LearningPapers · 4 Oct 2026 · Lin Qiu, Yao Liu, Diyi Hu, Hanqing Zeng, Onur Gungor, Chujie Chen, Jiayi Liu, Ji…
- What Will Post-Training Fix? Per-Problem Gains Are Shared Across Independent RL Runs, and Existing Checkpoints Predict Them Better Than A Priori SignalsPapers · 4 Oct 2026 · Xiaoxian Duan
- Outcome-Guided On-Policy Self-DistillationPapers · 4 Oct 2026 · ZheXu Wang, Mao-Lin Luo, Yankun Hong, Zi-Hao Zhou, Bo Ye, Jian Zhao, Xialiang To…
- Beyond Instruction Following: Learning Grounded Skill-Following with Skill ContractsPapers · 4 Oct 2026 · Jianghan Shen, Zhenjie Liu, Yue Li, Jie Huang, Siqi Luo, Yiming Cheng, Yizhi Yao…
- VERA: Scaling Verifiable Environments for Agentic co-EvolutionPapers · 5 Oct 2026 · Junqi Liu, Yongyang Pan, Zhuosong Jiang, Dongbai Li, Bo Zhang, Xitong Ling, Shen…
Latest sources
- Optimistic Verifiers Get Hacked: Reward Hacking Under an Exact Process OraclePapers · 16 Nov 2026 · Arunkumar V, Manoranjan Gandhudi, Gangadharan G. R., Arun Prakash, S. Senthilkum…
- AuXSpec: Learning to Autoformalize Program Specifications via Executable PostconditionsPapers · 16 Nov 2026 · Haocheng Wang, Weixuan Yuan, Florian Hübler, Yinya Huang, Zhijiang Guo, Sorrach…
- SpeCal: Spectral Calibration for Unsupervised RLVRPapers · 16 Nov 2026 · Kai Tang, Xing Zheng, Haobo Wang, Guangcheng Zhu, Shenzhi Yang, Zhengqing Zang,…
- Low-Latency LLM-Based Streaming Multi-Talker ASR with Verifiable RewardsPapers · 14 Nov 2026 · Jing Pan, Ruizhi Li, Ju Lin, Jing Zheng, Florian Metze
- Policy Optimization With Multiple Verifiers via Pareto RankingsPapers · 14 Nov 2026 · Kai Yamashita, Shohei Taniguchi, Hiroki Furuta, Masahiro Suzuki, Yutaka Matsuo
- PaperCritic: Training AI Reviewers to Assess the Soundness of PapersPapers · 13 Nov 2026 · Hyun Ryu, Ji Yong Cho, Eunho Yang, Moontae Lee, June Yong Yang, Sean Welleck, Ca…
- Benchmarks Don't Talk Back: Learning Through Self-DisagreementPapers · 12 Nov 2026 · Soheil Abbasloo, Peng Cheng
- Negative-Only Policy Optimization for One-Sided Verifiable RewardsPapers · 12 Nov 2026 · Jiacheng Xu, Shuo He, Fuxiang Zhang, Chaojie Wang, Bo An
- Reward-Driven Collider Physics Challenges for Self-Improving Agentic AI via Reinforcement LearningPapers · 11 Nov 2026 · Alexander Yue, Qibin Liu, Julia Gonski
- Honesty Is a Race: Predicting When Verifiable-Reward RL Teaches a Model to BluffPapers · 11 Nov 2026 · Nathaniel Bottman, Alexei Oblomkov
- The Illusion of Diversity: Aligning LLM Exploration via Effective EntropyPapers · 11 Nov 2026 · Xiaoliang Fu, Jiaye Lin, Yangyi Fang, Cong Qin, Binbin Zheng, Chaowen Hu, Zekai…
- Rethinking "RL Generalizes, SFT Memorizes": The Role of SFT DataPapers · 11 Nov 2026 · Yunlong Hou, Fengzhuo Zhang, Yuan Cheng, Jiachun Pan, Xingyao Li, Zhuoran Yang