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3,204 results for “keyword:"reinforce"” in ICLR 2027. 652 withdrawn or desk rejected listed apart.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]SpinningRL: Boosting RLVR Efficiency with Theoretical Reward Gain Modeling and Adaptive UCB Sampling▲1.9k3.67
[PDF]UPAO: Unbounded Positive Asymmetric Optimization for Breaking the Exploration–Stability Dilemma in RL▼1.2k1.67
[PDF]Rethinking Muon Beyond Pretraining: Spectral Failures and High-Pass Remedies for VLA and RLVR▼4.5k2.67
[PDF]A World Model Can Predict the Future Without Knowing Its Cause: Interventional Evaluation of Action-Conditioned World Models▲3.0k2.33
[PDF]TRUER: Test-Time Reward Correction Using an Error-Aware Rectifier for Reinforcement Learning▲6.1k2.00
[PDF]Inverse Reinforcement Learning without an Optimal Demonstrator: A Feasible Reward Set Approach▼4.3k2.00
[PDF]ThinkTwice: Jointly Optimizing Large Language Models for Reasoning and Self-Refinement▲9.2k2.67
[PDF]Bifocal Self-Rewarding: Aligning Answer Sufficiency with Visual Fidelity in VLM Reasoning▲3.0k2.33
[PDF]Leader-Follower Games with Policy Recommendation: Reinforcement Learning under a Preservation Constraint▼5.8k2.33
[PDF]SERA: Scale-Equalized Rollout Allocation for Maximum Likelihood Reinforcement Learning▼1.2k3.00
[PDF]Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost▲5.4k3.00
[PDF]Feedback Manipulation Regularization: Enabling Offline Agent Alignment for Imitation Learning▼5.9k2.50
[PDF]MAMR-GRPO: Reinforcement Learning with Execution-Structured Credit for Multi-Agent LLMs▼1611.50
[PDF]From-Base RLVR for Verify-Only Judges: A Rule-Based Reward Turns Base Models into Trajectory Auditors▲11.00
[PDF]Critical Decision Capacity: Bottleneck vs. Substitutable Degradation under Action Availability▼1.2k1.67
[PDF]Where, What, and When: Structured Intra-Response Advantage Redistribution for LLM Reasoning▼1361.33
[PDF]EPIC: Rethinking Trust Regions for Autoregressive LLM Policies via Exact-KL Prefix Importance-ratio Clipping▼1.2k1.67
[PDF]In Their Own Words: Reasoning Traces Tailored for Small Models Make Them Better Reasoners▲2843.00
[PDF]Rewarding the Graph Behind the Chain: Topology-Aware Process Supervision for RL and Reasoning Distillation▲3922.67
Withdrawn or desk rejected (652)
[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