NeurIPS 2026 reviews are up: reviews, scores, rebuttals and meta-reviews for 7,877 papers. See the highest rated
acceptodds: the papers of ICLR 2027
121 results for “keyword:"rlvr"” in ICLR 2027. 20 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Not All Reasoning Generalizes: A Case Study on Learning Generalizable Reasoning Strategies in RLVR▲3952.67
[PDF]Where Does RLVR Act? A Conserved Token Ledger for What Post-Training Adds to a Base Model▼4.3k2.00
[PDF]Same Reward, Different Ability: A Single-Variable Intervention Shows Task Formulation Governs What Spatial RLVR Learns▲3952.67
[PDF]Underused Verifier Signals? Refine and Replay for Multi-Constraint Instruction Following▼1.2k1.67
[PDF]WHICH VERIFIER ERRORS REACH THE GRADIENT? A MOMENT DECOMPOSITION FOR AUDITING GROUP- RELATIVE REINFORCEMENT LEARNING▼5.8k2.33
[PDF]Residual Visual Credit Optimization: Conserved Evidence Routing for Multimodal Reinforcement Learning▼4.3k2.00
[PDF]The Vanishing Middle: Reinforcement Learning Erases the Uncertain Category in Ordinal Classification▲5.4k3.00
[PDF]When RL Suppresses Its Own Vocabulary: Recovering Reasoning Diversity in Puzzle-to-Math Transfer▲3952.67
[PDF]ROAST: Reducing Overthinking in Reasoning via Advantage Reshaping and State-aware Termination▼4.3k2.00
[PDF]STABLE ALIGNMENT: ADAPTIVE KL CONTROL WITH GROUP-NORMALIZED ADVANTAGE ESTIMATION FOR RLHF▲11.00
[PDF]Riding the Waves of Uncertainty: Distributional Value Learning for LLMs with Verifiable Rewards▼4.3k2.00
[PDF]SpinningRL: Boosting RLVR Efficiency with Theoretical Reward Gain Modeling and Adaptive UCB Sampling▲1.9k3.67
Withdrawn or desk rejected (20)
[PDF]Gold-LP: Data Selection for Vision-Language Reinforcement Learning with Verifiable RewardsWithdrawn1.67
[PDF]Think Ontologically: Internalizing Neuro-Formal State Invariants for Robust Conversational Memory in Large Language Model AgentsWithdrawn1.67