Verifiable Rewards

Follow this topic Ask about this topic

Recent momentum

-14%

6 papers in the last 28 days · 0.1% of indexed attention

Twelve weeks of publication activity for this topic as it is defined today.

Weekly history

Recent digests

What was published in this topic, kept on the site without email delivery.

Period ending 2026-09-21

1 new paper

A weekly snapshot of new work published in Verifiable Rewards.

143 papers

Latest in Verifiable Rewards

Browse all topics →

When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models
Sep 17, 2026Jaejun Shim, HyunJin Kim, Young Jin Kim +1Large Reasoning Models Efficient Inference
CircuitLens: Reasoning Circuits as Data Selection Signals for Reinforcement Learning with Verifiable Rewards
Sep 7, 2026Zhuofan Chen, Ziqian Jiao, Yikai Cui +3Reinforcement Learning With Verifiable Reward Verifiable Rewards
FiMI Banking: A Sovereign Model for Indian Retail Banking
Sep 3, 2026NPCI AI Research Team, Aman Kumar, Asit Desai +15Banking Verifiable Rewards
DE-Venus: A Data-Efficient RLVR Framework for Large Language Models
Sep 3, 2026Shenzhi Yang, Guangcheng Zhu, Kai Tang +11Reinforcement Learning With Verifiable Reward Verifiable Rewards
Jina-OCR-v1: Efficient Document Parsing with Speculative Decoding and Dense Verifiable Rewards
Sep 2, 2026Alejandro Barón García, Feng Wang, Emilia Garcia Casademont +1Deepseek-Ocr Speculative Decoding
Where the Verifier Fails: A Category-Level Audit of Reward Signals in RLVR
Sep 1, 2026Esther XinVerifiable Rewards Reinforcement Learning With Verifiable Reward
Mechanism Design for Generative Engines: From Exploitation toward Win-Win Outcomes
Aug 11, 2026Chen Xu, Zitian Guo, Chenyan XiongIncentives Citations
PAIR: Pairwise-Aware Inclusion Reweighting for Adaptive Rollout Allocation in RLVR
Aug 11, 2026Pixel Nomand, Elena Voss, Marcus Hale +1Reinforcement Learning With Verifiable Reward Verifiable Rewards
ConRub-Med: Reinforcement Learning with Consensus Rubrics for Open-Ended Medical Question Answering
Aug 11, 2026Taojie Zhu, Yuan Xia, Tao Sun +8Verifiable Rewards
Improving Generalization Robustness of Multimodal RLVR
Aug 9, 2026Pengfei Zhou, Zhiwei Tang, Xiaopeng Peng +11Reinforcement Learning With Verifiable Reward Verifiable Rewards
MedCalc-R1: Knowledge-Guided Reward Framework for Medical Mathematical Reasoning
Aug 9, 2026Haotian Wang, Lian Yan, Xingzhi Yao +4Reinforcement Learning With Verifiable Reward Verifiable Rewards
StructReward: Efficient Structured Process Rewards for Self-Correcting Multimodal Reasoning
Aug 8, 2026Yifan Li, Ruxin Sun, Tongzhou ZhaoReliable Medical Process-Level Reward Model Evaluation Framework Multimodal Reasoning
Group-Reflective Self-Distillation for Agentic Reinforcement Learning
Jul 30, 2026Binbin Zheng, Zijun Xie, Guanqun Zhao +4Unsupervised On-Policy Self-Distillation Agentic Reinforcement-Learning Framework
From RLVR to RLSVR: Task Transformation Induces Self-Verifiable Rewards for Open-Ended LLM Self-Improvement
Jul 26, 2026Qinsi Wang, Jing Shi, Huazheng Wang +8Reinforcement Learning With Verifiable Reward Verifiable Rewards
ISO: An RLVR-Native Optimization Stack
Jul 21, 2026Hanqing Zhu, Wenyan Cong, Zhizhou Sha +8Reinforcement Learning With Verifiable Reward Optimizer Design
Off-Context GRPO: Learning to Reason on Hard Problems using Privileged Information
Jul 21, 2026Priyank Agrawal, Ankur Samanta, Shervin Ghasemlou +4Reinforcement Learning With Verifiable Reward Group Relative Policy Optimization
Adopting Reinforcement Learning with Verifiable Rewards for Molecular Generation
Jul 21, 2026Mingxuan Ouyang, Hao Lan, Wanyu LinMolecular Generation Verifiable Rewards
Beyond Entropy: Correctness-Aware Advantage Shaping via Contrastive Policy Optimization
Jul 16, 2026Weiwen Xu, Jia Liu, Hou Pong Chan +4Reinforcement Learning With Verifiable Reward Verifiable Rewards
Non-vacuous Generalization Bounds for Reinforcement Learning with Verifiable Rewards
Jul 16, 2026Yuxuan Zhu, Rohan Alur, Daniel KangReinforcement Learning With Verifiable Reward Verifiable Rewards
A Learning-Rate-Gated Failure of GRPO in a Small Language and Vision-Language Model Web Agent: A Controlled Null and Its Mechanism
Jul 14, 2026Chengguang Gan, Zhixi Cai, Yunhao Liang +3Group Relative Policy Optimization Reinforcement Learning With Verifiable Reward
SCOPE-RL: Optimizing Reasoning Paths Before and After Success
Jul 13, 2026Xiaojian Liu, Han Xu, Jianqiang Xia +6Reinforcement Learning With Verifiable Reward Verifiable Rewards
Strategic Bargaining in Multi-Buyer Markets: Reinforcement Learning from Verifiable Rewards for LLM Negotiations
Jul 7, 2026Shuze Daniel Liu, Claire Chen, Jiabao Sean Xiao +2Negotiation Matching Markets
Weak-to-Strong Generalization via Direct On-Policy Distillation
Jul 6, 2026Shiyuan Feng, Huan-ang Gao, Haohan Chi +7On-Policy Distillation Deep Reinforcement Learning
Reward-Gated On-Policy Distillation
Jul 4, 2026Mohammad Sadegh Akhondzadeh, Vijay Lingam, Atula Tejaswi +3On-Policy Distillation Rp-Opsd
Procedural Memory Distillation: Online Reflection for Self-Improving Language Models
Jul 1, 2026Ye Liu, Srijan Bansal, Bo Pang +6Unsupervised On-Policy Self-Distillation Verifiable Rewards
Beyond Next-Token Prediction: An RLVR Proof of Concept for Tool-Use Agents on Atlassian Workflows
Jul 1, 2026Karthikeya Aditya Vissa, Sankalp Mane, Ananya Mantravadi +2Reinforcement Learning With Verifiable Reward Verifiable Rewards
Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations
Jul 1, 2026Mehul Damani, Isha Puri, Idan Shenfeld +1Reinforcement Learning With Verifiable Reward Verifiable Rewards
Verifiable Rewards for Calibrated Probabilistic Forecasting
Jun 30, 2026Sadanand Singh, Allam Reddy, Manan ChopraVerifiable Rewards
Experience Augmented Policy Optimization for LLM Reasoning
Jun 29, 2026Jinda Lu, Kexin Huang, Junkang Wu +7Reinforcement Learning With Verifiable Reward Large Language Model Reasoning
LatentRevise: Learning from Zero-Hit Reasoning
Jun 29, 2026Yiqiu Guo, Xueting Han, Qi Jia +2Reinforcement Learning With Verifiable Reward Efficient Latent Reasoning
BV-Blend: Uncertainty-Weighted Historical Baselines for Stable Critic-Free RL with Verifiable Rewards
Jun 27, 2026Yupeng Chang, Yuan Wu, Yi ChangReinforcement Learning With Verifiable Reward Critic-Free Reinforcement Learning
Tandem Reinforcement Learning with Verifiable Rewards
Jun 26, 2026Difan Jiao, Raghav Singhal, Robert West +1Reinforcement Learning With Verifiable Reward Verifiable Rewards
PerturbCellRL: Verifier-Guided Reinforcement Learning for Single-Cell Perturbation Prediction
Jun 26, 2026Dongxia Wu, Mingyu Li, Yuhui Zhang +4Single-Cell Perturbation Prediction Single-Cell Rna Sequencing
ExTra: Exploratory Trajectory Optimization for Language Model Reinforcement Learning
Jun 23, 2026Wenyang Hu, Junxiang Jia, Zhen Shu +3Reinforcement Learning With Verifiable Reward Reasoning Trajectory
What are Key Factors for Updates in RL for LLM Reasoning?
Jun 21, 2026Peidong Wang, Demi Wang, Xufang Luo +5Reinforcement Learning With Verifiable Reward Large Language Model Reasoning
Mat-Pref: Verifiable-Reward Training Improves Compositional Reasoning in Inorganic Materials
Jun 20, 2026Sarrah R. Mikhail Leung, Taehan Kim, Jeongbin ParkVast Chemical Space Verifiable Rewards
Process-Verified Reinforcement Learning for Theorem Proving via Lean
Jun 18, 2026Minsu Kim, Se-Young YunReinforcement Learning With Verifiable Reward Reliable Medical Process-Level Reward Model Evaluation Framework
Learning from Own Solutions: Self-Conditioned Credit Assignment for Reinforcement Learning with Verifiable Rewards
Jun 17, 2026Yingyu Shan, Yuhang Guo, Zihao Cheng +7Reinforcement Learning With Verifiable Reward Credit Assignment
Sparsity Curse: Understanding RLVR Model Parameter Space from Model Merging
Jun 16, 2026Chenrui Wu, Zexi Li, Jiajun Bu +2Reinforcement Learning With Verifiable Reward Model Merging
STRIDE: Strategic Trajectory Reasoning via Discriminative Estimation for Verifiable Reinforcement Learning
Jun 14, 2026Qinjian Zhao, Zhihao Dou, Dinggen Zhang +10Reinforcement Learning With Verifiable Reward Verifiable Rewards
Understanding Diversity Collapse in RLVR via the Lens of Overtraining
Jun 13, 2026Suqin Yuan, Jinkun Chen, Jiyang Zheng +6Reinforcement Learning With Verifiable Reward Verifiable Rewards
TRACE: A Unified Rollout Budget Allocation Framework for Efficient Agentic Reinforcement Learning
Jun 9, 2026Heming Zou, Qi Wang, Yun Qu +9Agentic Reinforcement-Learning Framework Rollout
Beyond Uniform Token-Level Trust Region in LLM Reinforcement Learning
Jun 9, 2026Renjie Mao, Xiangxin Zhou, Lvfang Tao +7Reinforcement Learning With Verifiable Reward Verifiable Rewards
CapRL++: Unified Reinforcement Learning with Verifiable Rewards for Dense Image and Video Captioning
Jun 8, 2026Penghui Yang, Long Xing, Xiaoyi Dong +10Video Captioning Multimodal Pretraining
Reasoning Arena: Trace Tournaments When Verifiable Rewards Fall Short
Jun 8, 2026Han Zhou, Adam X. Yang, Laurence Aitchison +2Reinforcement Learning With Verifiable Reward Verifiable Rewards
A Regret Minimization Framework on Preference Learning in Large Language Models
Jun 8, 2026Suhwan Kim, Taehyun Cho, Geon-Hyeong Kim +4Reinforcement Learning From Human Feedback Preference Learning
Hardening Agent Benchmarks with Adversarial Hacker-Fixer Loops
Jun 8, 2026Ziqian Zhong, Ivgeni Segal, Ivan Bercovich +3Hacking Adversarial Evaluation
Momentum for Reasoning: Dense Intrinsic Signals in Policy Optimization
Jun 7, 2026Hao Chen, Zhanming Shen, Liyao Li +8Reinforcement Learning With Verifiable Reward Verifiable Rewards
PRPO: Perception-Reinforced Policy Optimization via Token-Level Dynamic Advantage Reshaping
Jun 7, 2026Qiming Li, Tianlun Li, Xiaolong Cheng +5Multimodal Reasoning Benchmarks Reinforcement Learning With Verifiable Reward
Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization
Jun 5, 2026Shizhe Xiang, Ke An, Wenlong Yu +4Reinforcement Learning With Verifiable Reward Multimodal Reasoning
Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces
Jun 3, 2026Nicolás Astorga, Nabeel Seedat, Mihaela van der SchaarPrompt Optimization Llm-Based Optimization Modeling
Reinforcement Learning from Rich Feedback with Distributional DAgger
Jun 3, 2026Rishabh Agrawal, Jacob Fein-Ashley, Paria RashidinejadReinforcement Learning With Verifiable Reward Unsupervised On-Policy Self-Distillation
Policy-Conditioned Counterfactual Credit for Verifiable Reinforcement Learning of Long-Horizon Language Agents
Jun 3, 2026Renwei MengReinforcement Learning With Verifiable Reward Verifiable Rewards
GRAIL: Gradient-Reweighted Advantages for Reinforcement Learning with Verifiable Rewards
Jun 3, 2026Tej Deep Pala, Vernon Toh, Soujanya PoriaReinforcement Learning With Verifiable Reward Verifiable Rewards
Rollout-Level Advantage-Prioritized Experience Replay for GRPO
Jun 3, 2026Gyeongtae Yoo, Sanghyeok Park, Soohyuk Jang +2Group Relative Policy Optimization Verifiable Rewards
GeoMin: Data-Efficient Semi-Supervised RLVR via Geometric Distribution Modeling
Jun 3, 2026Guangcheng Zhu, Shenzhi Yang, Haobo Wang +9Reinforcement Learning With Verifiable Reward Semi-Supervised Learning
Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots
Jun 3, 2026Guangcheng Zhu, Shenzhi Yang, Haobo Wang +7Reinforcement Learning With Verifiable Reward Verifiable Rewards
QUBRIC: Co-Designing Queries and Rubrics for RL Beyond Verifiable Rewards
Jun 2, 2026Rongzhi Zhang, Rui Feng, Zhihan Zhang +8Rubric-Based Reinforcement Learning Reinforcement Learning With Verifiable Reward
Right Makes Might: Aligning Verified Hidden States Empowers RL Reasoning
Jun 2, 2026Ziyue Wang, Aomufei Yuan, Yongfu Zhu +10Reinforcement Learning With Verifiable Reward Verifiable Rewards
Learning to Solve, Forgetting to Retain: Correct-Set Turnover in RLVR
Jun 2, 2026Chuanyu Qin, Chenxu Yang, Qingyi Si +3Reinforcement Learning With Verifiable Reward Verifiable Rewards

Sep 17, 2026 · cs.AIJ/K move · Enter open · S save

When2Think: Learning Difficulty-Aware Length Control for Efficient Hybrid Reasoning Models

Jaejun Shim, HyunJin Kim, Young Jin Kim, JinYeong Bak

Sungkyunkwan University · Microsoft

Large Reasoning Models (LRMs) achieve strong performance on complex tasks but exhibit systematic inefficiency: they often overthink easy problems and underthink hard ones. Existing approaches based on uniform length penalties or rigid routing incur an efficiency tax, trading reduced computation on easy instances for accuracy loss on hard instances. We formulate efficient reasoning as an instance-adaptive computation allocation problem and propose When2Think, a post-training framework for hybrid reasoning that dynamically allocates computation based on problem difficulty. Our method introduces Instance-level Difficulty-Aware Control (IDAC), a reward-shaping mechanism that leverages pre-computed reference statistics (accuracy and token usage) to regulate reasoning depth. Combined with verifier-based rewards and batch-wise standardized advantages, IDAC enables stable critic-free optimization without learned reward models or online reference-model queries. When2Think encourages direct answering on easy instances while preserving extended reasoning on hard instances, thereby learning when to use System 1 (NoThink) versus System 2 (Think). Experiments on mathematical benchmarks demonstrate improved accuracy-efficiency trade-offs: on AIME24, Pass@3 increases by 10.0% while token usage is reduced by 27.9% relative to the base model, and on AIME25, When2Think achieves 40.0% Pass@3, outperforming compression and routing-only baselines.

Large Reasoning Models Efficient Inference Verifiable Rewards

Open paper Ask about it PDF