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
1,984 results for “area:"reinforcement learning"” in ICLR 2027. 387 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Reward Reasoning for Its Gain over a Snap Judgment: Inverse-RL Cold Start of GUI Agents with an Adversarial Critic▲5.4k3.00
[PDF]An Anchored Policy Regularizer for Deep Constrained Multi-Agent Reinforcement Learning under Tight Cost Budgets▲5103.00
[PDF]Back to Basics: Revisiting Exploration in Reinforcement Learning for LLM Reasoning via Generative Probabilities▲3922.67
[PDF]AlphaG-OPD: Reliability-Gated Sibling Counterfactuals for On-Policy Distillation in Symbolic Alpha Factor Discovery▼1361.33
[PDF]FDR-Controlled Selection in Reinforcement Learning via Distributional Likelihood Ratios▲13k2.33
[PDF]EM-OPD: Evidence-Conditioned Multi-Expert On-Policy Distillation for Pathology Report Generation▲3.0k2.33
[PDF]Quantile of Means: A Bonus-Free Ensemble Method for Minimax Optimal Reinforcement Learning▲20k2.67
[PDF]H-OSIRIS: Hierarchical Layout-Aware Analog Circuit Sizing and Footprint Optimization using Deep Reinforcement Learning▼4.3k2.00
[PDF]Same Groups, Different Values: Decomposing Step-Level Credit Assignment for LLM Agents▲6.1k2.00
[PDF]TraceStencil: Signed Temporal Neighborhoods for Token-Level Policy Optimization in RLVR▼1.2k1.67
[PDF]CALIPER: Compute-Aware Local Intervention and Targeted Policy Updates for Tool-Augmented Agents▼1.2k1.67
[PDF]SARC: Interpretable State-Adaptive Reward Composition for Sparse Reward Reinforcement Learning▲3.0k2.33
[PDF]Provably avoiding over-optimization in Direct Preference Optimization without knowing the data distribution▲3.0k2.33
[PDF]ROAST: Reducing Overthinking in Reasoning via Advantage Reshaping and State-aware Termination▼4.3k2.00
[PDF]When Zero Cost Does Not Mean Safe: Response Delay and Policy Delivery in Resource-Constrained Reinforcement Learning▼1.3k1.75
[PDF]Beyond Safe Demonstrations: Failure-Informed Flow Policies for Offline Safe Reinforcement Learning▲5103.00
[PDF]MileGPO: Milestone Inference with Local Evidence for Graph-Based Policy Optimization of Long-Horizon LLM Agents▼1.2k1.67
[PDF]Remembering What Changes the Future: Learning to Compress Agent Histories for Long-Horizon Tasks▼4.3k2.00
Withdrawn or desk rejected (387)
[PDF]Population Contracts for Scalable Language-Guided Multi-Robot Planning and ControlDesk rejected
[PDF]What Should I Try Next? Decision-Relevant Counterfactual Information Gain for Active World ModelsWithdrawn1.00
[PDF]Recoverable Coordination Distillation for Decentralized Multi-Agent Reinforcement LearningWithdrawn1.67
[PDF]Implicit Strategic Optimization: Prediction-Aware Long-Horizon Learning for LLM AgentsDesk rejected1.67