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
3,204 results for “keyword:"reinforce"” in ICLR 2027. 652 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Credit Where the Cut Happens: Candidate Contraction for Repository-Level Code Localization▲43.67
[PDF]Learning to Teach, Learning to Play: Dual Reinforcement Learning with Active Trajectory Inquiry▼4.3k2.00
[PDF]AMHSTrafficLab: An Industrial Benchmark for Routing and Regional Traffic Control in Large-Scale Resource-Competitive Transport Networks▼4.3k2.00
[PDF]Safe Executions Can Hide Policy Failure: A Proposal-Level Audit of Hybrid Control in Synthetic Interviews▲2.0k1.50
[PDF]EvoMind: A Self-Evolving Alpha Factor Mining Agent via Process-Reward Reinforcement Learning▼5.8k2.33
[PDF]RANA: Accelerating Multi-Turn Agentic Reinforcement Learning with Speculative Decoding▼4.3k2.00
[PDF]P-BFM: Perceptive Behavioral Foundation Models for Humanoid Control via Unsupervised Reinforcement Learning▲133.33
[PDF]Enhancing Robustness of Small-Scale Models for Text-to-SQL via Semantic Enhancement and Noise-Aware Methods▼1.2k1.67
[PDF]FlowWeaver: Weaving Reasoning Paths with Cross-Trajectory Flow for Fine-Grained Credit Assignment▲3922.67
[PDF]How Should Teachers Be Prepared? RL on Student-Induced States for On-Policy Distillation▼4.5k2.67
[PDF]Constrained Command-Conditioned Reinforcement Learning with Bandit Strategy Selection in Real-Time Strategy Games▼4.3k2.00
[PDF]Where Does Task Identity Live? FLAT: A Provenance-Complete Fixed-Log Audit for Offline Task Identification▼4.3k2.00
[PDF]LEARNING HOW TO BE RISK-SENSITIVE: STATE-DEPENDENT RISK FUNCTIONALS FOR REINFORCEMENT LEARNING▲3922.67
[PDF]Agents Verify Their Assumptions, Not the Specification: Interpretation Lock-in in Autonomous Coding Agents▼5.3k1.33
[PDF]Enhancing Large Language Models with Decision-Relevant Knowledge for Reinforcement Learning Tasks▼5.8k2.33
[PDF]Learning Chunk Values from Partial Execution in Offline-to-Online Reinforcement Learning▼5.8k2.33
Withdrawn or desk rejected (652)
[PDF]Topological Necessities: Mechanism-Invariant Strategic Subgoals for Cross-Embodiment Goal-Conditioned ControlWithdrawn1.67
[PDF]Q-Guided Action-Transport Editing for Real-World Reinforcement Learning of Vision-Language-Action ModelsDesk rejected2.33
[PDF]FlowErase-RL: Rethinking Concept Erasure as Reward Optimization in Flow Matching ModelsWithdrawn1.33
[PDF]UniOPSD: Unifying Outcome and Hindsight Feedback for Agentic Reinforcement LearningWithdrawn1.67
[PDF]VA-Judger: Reward Modeling from Human Preference Feedback for Joint Video-Audio GenerationDesk rejected
[PDF]Granularity-Adaptive Credit Assignment for Long-Horizon LLM Agent Reinforcement LearningDesk rejected2.00
[PDF]Beyond Instruction Following: Learning Grounded Skill-Following with Skill ContractsWithdrawn1.67