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
230 results for “keyword:"policy optimization"” in ICLR 2027. 55 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]Beyond Expected Returns: Time-Average Regularized Policy Optimization for Trajectory-Level Performance▲6.1k2.00
[PDF]Train Ahead, Distill Back: Bootstrapping On-Policy Self-Distillation for Large Language Models▲3972.67
[PDF]Let Intuition Teach Deliberation: Rewarding Prefix Success Potential in Reasoning Models▼4.3k2.00
[PDF]Proper Scoring under Group Reward Normalization: Target Distortion and Exact Finite-Group Updates▼4.3k2.00
[PDF]Let Credit Follow Computation: Architecture-Aware Credit Transport for Large Language Model Reinforcement Learning▼1.2k1.67
[PDF]Learn What’s Left, Not What’s Mastered: Saturation Aware Advantage Reweighting for Multi-Reward Policy Optimization▼5.8k2.33
[PDF]Follow the Improvement: Guaranteed Policy Optimization by Tracking Proximal Ascent Targets▼5.8k2.33
[PDF]Revealing the Emergent Learning Mechanisms of Critic Models in PPO for LLM Reinforcement Learning▲3972.67
[PDF]CHIP: One Chi-Squared Ball for Both Errors of Reinforcement Learning in Large Language Models▲5.4k3.00
[PDF]DESIGN THEFEEDBACK, NOTJUST THEREWARD: ENVIRONMENTS FOROPEN-ENDED REINFORCEMENT LEARNING▼4.3k2.00
[PDF]When Return Bounds Do Not Control Update Weights: Prediction Rewards in Multi-Turn LLM Agents▼5.9k2.50
[PDF]Beyond Policy Rollouts: Embedding-Space Directional Exploration with Anchored Noise for LLM RLVR▼4.5k2.67
[PDF]When Policies Drift, Prefixes Matter: Prefix-Normalized Policy Optimization for LLM Reinforcement Learning▼4.3k2.00
[PDF]Exploring More, Reasoning Better: Stepwise Risk-Sensitive GRPO for Diffusion Language Models▼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]MileGPO: Milestone Inference with Local Evidence for Graph-Based Policy Optimization of Long-Horizon LLM Agents▼1.2k1.67
[PDF]Self-Improving Bayesian Flow Networks via Group Relative Policy Optimization for Structure-Based Drug Design▲3.0k2.33
[PDF]Dual-Channel Robust Group-Relative Policy Optimization via Advantage and Sequence-Weight Estimation▼1.2k1.67
[PDF]STAR-GRPO: Canonical Anchoring and Reliability-First Advantages against Representation-Dependent Reward Hacking▼4.3k2.00
[PDF]Consensus-Breaking Re-rollout: Recovering Missing Action Contrasts for Long-Horizon Agent Reinforcement Learning▼4.3k2.00
[PDF]ReDiPPO: Reference-Guided Value Calibration and Discrepancy-Aware Token Reweighting for Mathematical Reasoning▲3.0k2.33
[PDF]Matched Compute Is Not Matched Signal: Where the Gradient Goes in Group-Relative Reinforcement Learning▼1361.33
[PDF]Pareto-GRPO: Prompt-Local Pareto Credit Assignment for Efficient Search-Augmented Reasoning▼1.2k1.67
Withdrawn or desk rejected (55)
[PDF]Implicit Strategic Optimization: Prediction-Aware Long-Horizon Learning for LLM AgentsDesk rejected1.67
[PDF]Learning What to Share: Latent Representations for FedRL with Observation DistractorsDesk rejected1.67
[PDF]Hierarchical Safety-Oriented Dense RL with Refined Credit Assignment for Tokenized Multi-Agent Traffic SimulationWithdrawn1.75
[PDF]Verifier-Induced Strategy Collapse: Family-Correlated False Negatives Eliminate Valid Strategies While Capability Metrics ImproveDesk rejected