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
188 results for “keyword:"reinforcement learning with verifiable rewards"” in ICLR 2027. 26 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Which Updates Erase What the Base Model Knew? Optimizer-Conditioned Attribution of Reasoning-Support Loss in RLVR▼5.8k2.33
[PDF]On Delayed Learning in Reinforcement Learning with Verifiable Rewards: Provable Laws of Feedback and Recovery
[PDF]KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization▲5103.00
[PDF]DStreamer: Acceptance-Aligned Diffusion Streaming for High-Throughput Serving and Online RLVR▲3952.67
[PDF]When Do RTL Verifiers Lie? Measuring Proxy-Reward Overoptimization in LLM Hardware Design▼4.5k2.67
[PDF]How to Train Your Little Dragon: Teaching a Small Language Model to Construct and Refine GPU Optimization Scripts▼5.8k2.33
[PDF]When Sharpening Becomes Collapse: Sampling Bias and Semantic Coupling in RL with Verifiable Rewards▼1.2k1.67
[PDF]STRATA: Preserving Rare Solution Strategies in Reinforcement Learning with Verifiable Rewards▼1361.33
[PDF]When LoRA Rank Matters in RLVR: Saturation-Gated Scaling and Off-Principal Initialization▼1361.33
[PDF]Balancing Reference Guidance and Free Generation in Trajectory Rollouts for Reasoning RL▲5103.00
[PDF]One Self, Many Masks: Language Models Have a Self That Persists Beneath Their Personas▼1.2k1.67
[PDF]Rethinking Training–Inference Mismatch in LLM Reinforcement Learning: Where It Arises and How to Correct It▲3952.67
[PDF]When Does Branching Pay? An Exact Variance Analysis of Tree-Structured Policy Gradients▼4.3k2.00
Withdrawn or desk rejected (26)
[PDF]HackFree-GRPO: Detecting and Mitigating Reward Hacking in RLVR- Trained Code AgentsWithdrawn2.00
[PDF]Dissecting Reinforcement Learning: Mechanisms Behind Compositional Reasoning in LLMsWithdrawn1.67
[PDF]Mitigating Modality Interference for Unified Reasoning and Perception in Multimodal Large Language ModelsDesk rejected2.00
[PDF]AnchorCredit: Output-Anchored Credit Assignment for Structured Generation with Multiple Verifiable RewardsDesk rejected2.67