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
3,169 results for “keyword:"reinforcement learnin"” in ICLR 2027. 642 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Fully Decentralized Cooperative Multi-Agent Reinforcement Learning is A Context Modeling Problem▼5.8k2.33
[PDF]OmniInstruct: Instruction‑Guided Audio-Video Editing via Universal Dataset and Reward Optimization
[PDF]RubricEvo: Sustaining Learning Signals via Evolving Graph-based Multi-Level Rubrics in Open-Ended Reinforcement Learning▲13k2.00
[PDF]Code, Not Chains-of-Thought: Localizing Guideline-Adherence Risk by Compiling Guidelines into MedCode▲11.00
[PDF]RILO: Feeding Implicit Process Rewards Back into Visual Reasoning for Industrial Anomaly Understanding▼1.3k1.75
[PDF]SIGMA: Interaction-Conditioned Geometry Tokenization for Cross-Shape Humanoid Manipulation▲3.0k2.33
[PDF]When Every Rollout Fails: Splicing Learner-Conditioned Options into Long-Horizon Agent RL▼5.8k2.33
[PDF]PhysEvolve: Verifier-Grounded Self-Evolution for Physical Reasoning with Executable Worlds▼5.9k2.50
[PDF]CausalDrive: Breaking Motion Inertia in VLA-based Autonomous Driving by Aligned Semantic Intervention▼1361.33
[PDF]When Mismatch Misleads: Stabilizing Low-Precision Reinforcement Learning via Reliable Correction▼4.5k2.67
[PDF]Learning to Zoom at the Right Difficulty: Dynamic Curricula for Visual Tool-Use Reinforcement Learning▲5103.00
[PDF]MatBak: Targeted-Behavior Adversarial Attacks on Multiple Reinforcement Agents via Preference-Based Intention Policies▼1.2k1.67
[PDF]Hindsight Is 20/20: Adaptive Credit Assignment via Realized Futures for Long-Horizon LLM Agents▼4.3k2.00
[PDF]The Correction Budget: When Test-Time Refinement Can and Cannot Fix World-Model Rollouts▼1611.50
[PDF]Manifold Bandits: Bayesian Curriculum Learning over the Latent Geometry of Large Language Models▼1.2k1.67
[PDF]Cross-Behavior Policy Optimization: Unified Learning from Offline Demonstrations and On- and Off-Policy Rollouts via a Shared Regression Target▼4.5k2.25
[PDF]Localized Deep Neural Actor-Critic for Decentralized MARL: Finite-Time Global Convergence Guarantees▼5.8k2.33
[PDF]DPR: From High-Entropy Tokens to Learning Claims — Matched Evaluation for Token-Selective LLM Reinforcement Learning▼1361.33
Withdrawn or desk rejected (642)
[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