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230 results for “keyword:"policy optimization"” in ICLR 2027. 55 withdrawn or desk rejected listed apart.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]When Evaluation Changes the Conclusion: Measuring the Reliability of Small RL Gains in Reasoning LLMs▼4.3k2.00
[PDF]Low-Confidence Remasking Traps Flexibility: Realizing Arbitrary-Order Potential for Diverse Rollouts in Diffusion LLMs▲5103.00
[PDF]Why Sample What You Can Enumerate? Exact Policy Optimization for Genomic Tool Selection▲5103.00
[PDF]TAIRL: Optimizing Multi-Turn Open-Ended Dialogue via Temporal Patterns in Human Feedback▼4.3k2.00
[PDF]When Reward Doesn't See Everything: Modality-Blind Credit Assignment for Simultaneous Speech-To-Speech Translation▲3.9k1.67
[PDF]Using Experience Twice: Dynamic Process Rubrics for Privileged Token-Level Credit Assignment▲11k2.00
[PDF]SofT-GRPO: Surpassing Discrete-Token LLM Reinforcement Learning via Gumbel-Reparameterized Soft-Thinking Policy Optimization▲3.0k2.33
[PDF]FSPO: Policy-Consistent Risk and Pareto-Feasible Control for Budgeted LLM RL Post-Training▼4.3k2.00
Withdrawn or desk rejected (55)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