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
595 results for “keyword:"on policy"” in ICLR 2027. 111 withdrawn or desk rejected listed apart. clearsort:relevanceratingnewestmost read
[PDF]DStreamer: Acceptance-Aligned Diffusion Streaming for High-Throughput Serving and Online RLVR▲3952.67
[PDF]Resolvable-Effect Accounting for Tool-Calling Agents: Reward Bias and Evaluation Resolution▲11.00
[PDF]What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection▲3952.67
[PDF]Reinforcing LLM Latent Reasoning with Contextual Loops through On-Policy Flow-Map Self-Distillation▼1.2k1.67
[PDF]When Agents Collude: Weak-to-Strong On-Policy Distillation for Mitigating Strategic Deception in Multi-Agent Systems▼4.3k2.00
[PDF]Learning to Elicit: Co-Evolving Routing and Information Disclosure in Societies of Language Agents▼1361.33
[PDF]Can Native Safety Travel? Reusing Safety Pretraining Across Models via On-Policy Distillation▲3952.67
[PDF]Pay for Rollouts Only When Needed: Compute-Aware Routing for Language Model Distillation▼1.2k1.67
[PDF]BiFlow: First-Order Bilevel Coarse-to-Fine Flow Matching Policy for Continuous Control▼4.3k2.00
[PDF]When Does Teacher Feedback Hurt? Outcome-Aligned Reweighting for On-Policy Distillation▼4.3k2.00
[PDF]HARP: On-Policy Distillation of Hierarchically Routed Planning, Execution, and Revision Experts▼4.3k2.00
[PDF]ProjOPD: Conflict Projection for On-Policy Distillation in Agentic Reinforcement Learning▼1361.33
[PDF]From Traces to Recipes: Constructing and Distilling Reusable Procedural Knowledge into Language Models▲3.0k2.33
Withdrawn or desk rejected (111)
[PDF]Beyond the Local View: Predicting Correction Gains for Sparse On-Policy DistillationWithdrawn1.33