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
3,168 results for “keyword:"reinforcement learnin"” in ICLR 2027. 643 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Decoding Trajectory Forgetting: Continual Reinforcement Learning for Diffusion Large Language Models via Trajectory Alignment▼4.5k2.67
[PDF]GroundForm: Learning to Ground Autoformalization with Verified Hindsight Credit and Growing Memory▼4.3k2.00
[PDF]Reasoning Quality Matters: Combating Reasoning Collapse in LLM-based Embedding Learning▲5.4k3.00
[PDF]CrystalReasoner: Reasoning and RL for Property-Conditioned Crystal Structure Generation▼5.8k2.33
[PDF]Better Fixed-State Fidelity Need Not Improve Closed-Loop Performance in Quantized Neural Policies▼1361.33
[PDF]Learning from All-Failed Groups via First-Visit Coverage in Long-Horizon Agentic Tasks▼5.8k2.33
[PDF]Behavioral Response Spectroscopy: Pre-RL Responses Reveal Shared Structure in RL-Induced Behavioral Change▼1.2k1.67
[PDF]FocusDreamer: Task-Directed Model-Based Reinforcement Learning Guided by Return Relevance▲5.4k3.00
[PDF]Rethinking RL for LLM Reasoning: It’s Sparse Policy Selection, Not Capability Learning▼4.5k2.67
[PDF]Agentic-OPD: Recovering Forgotten Agent Capabilities via On-Policy Distillation for Long-Horizon Tasks▲6.1k2.00
[PDF]SAW-v2: Supervised Dual-Stream State Adaptive Weight for High-Dimensional Multi-Agent Reinforcement Learning▲13k2.33
[PDF]Where to Reuse, What to Propagate: Transition Reconstruction for Cross-Domain Offline Reinforcement Learning▼5.8k2.33
[PDF]Prorsa: Unleashing the Potential of Prefill-Decode Disaggregation in Agentic Reinforcement Learning▼5.8k2.33
[PDF]Teaching Thinking Models to Reason with Tools: A Full-Pipeline Recipe for Tool-Integrated Reasoning▲5103.00
[PDF]Diffusion-Augmented Markov Decision Processes for Maximum Entropy Reinforcement Learning▲5.4k3.00
[PDF]Distributionally Robust Average-Reward Reinforcement Learning: Finite-Sample Guarantees under Weakly Communicating▼4.5k2.67
[PDF]Not Which Path, but What Happens Before You Would Stop: What Reasoning Post-Training Changes▼1361.33
[PDF]Beyond Answer Correctness: Executable Derivation Faithfulness for Urban Spatial Reasoning▲9.2k2.67
[PDF]Average-Reward Policy Optimization via Discounting: Anytime and Global Linear Convergence▼4.3k2.00
[PDF]CEDAR: Concise, Evidence-grounded Driving Action Recommendation via Cascade Reasoning and Policy Refinement▼5.8k2.33
[PDF]Grounded-R1: Reinforcement Learning for Preemptive Hallucination Intervention and Grounded Generation▲3.0k2.33
Withdrawn or desk rejected (643)
[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]Never Stop Rewiring: Safe Continual Reinforcement Learning on Non-Resetting GraphsWithdrawn1.33
[PDF]Recoverable Coordination Distillation for Decentralized Multi-Agent Reinforcement LearningWithdrawn1.67