{"total":59,"rows":[{"id":"2602.12275","title":"On-Policy Context Distillation for Language Models","created":"2026-02-12","cited_by_count":186,"area":"distill"},{"id":"2602.12125","title":"Learning beyond Teacher: Generalized On-Policy Distillation with Reward Extrapolation","created":"2026-02-12","cited_by_count":184,"area":"lr"},{"id":"2604.00626","title":"A Survey of On-Policy Distillation for Large Language Models","created":"2026-04-01","cited_by_count":163,"area":"distill"},{"id":"2603.25562","title":"Revisiting On-Policy Distillation: Empirical Failure Modes and Simple Fixes","created":"2026-03-26","cited_by_count":145,"area":"distill"},{"id":"2605.03677","title":"Uni-OPD: Unifying On-Policy Distillation with a Dual-Perspective Recipe","created":"2026-05-05","cited_by_count":49,"area":"distill"},{"id":"2606.11709","title":"RLCSD: Reinforcement Learning with Contrastive On-Policy Self-Distillation","created":"2026-06-10","cited_by_count":45,"area":"lr"},{"id":"2604.13010","title":"Lightning OPD: Efficient Post-Training for Large Reasoning Models with Offline On-Policy Distillation","created":"2026-04-14","cited_by_count":33,"area":"lr"},{"id":"2604.08527","title":"Demystifying OPD: Length Inflation and Stabilization Strategies for Large Language Models","created":"2026-04-09","cited_by_count":30,"area":"distill"},{"id":"2605.07725","title":"SOD: Step-wise On-policy Distillation for Small Language Model Agents","created":"2026-05-08","cited_by_count":21,"area":"agents"},{"id":"2607.26057","title":"Pass the Baton: Trajectory-Relayed On-Policy Distillation","created":"2026-07-28","cited_by_count":18,"area":"distill"},{"id":"2605.12400","title":"OGLS-SD: On-Policy Self-Distillation with Outcome-Guided Logit Steering for LLM Reasoning","created":"2026-05-12","cited_by_count":16,"area":"lr"},{"id":"2605.13643","title":"Prefix Teach, Suffix Fade: Local Teachability Collapse in Strong-to-Weak On-Policy Distillation","created":"2026-05-13","cited_by_count":16,"area":"distill"},{"id":"2607.04763","title":"Multi-Turn On-Policy Distillation with Prefix Replay","created":"2026-07-06","cited_by_count":15,"area":"agents"},{"id":"2605.07396","title":"Rubric-based On-policy Distillation","created":"2026-05-08","cited_by_count":13,"area":"alignment"},{"id":"2605.07711","title":"SimCT: Recovering Lost Supervision for Cross-Tokenizer On-Policy Distillation","created":"2026-05-08","cited_by_count":12,"area":"distill"},{"id":"2601.16547","title":"CORD: Bridging the Audio-Text Reasoning Gap via Weighted On-policy Cross-modal Distillation","created":"2026-01-23","cited_by_count":11,"area":"lr"},{"id":"2601.21968","title":"OVD: On-policy Verbal Distillation","created":"2026-01-29","cited_by_count":11,"area":"lr"},{"id":"2605.12483","title":"Beyond GRPO and On-Policy Distillation: An Empirical Sparse-to-Dense Reward Principle for Language-Model Post-Training","created":"2026-05-12","cited_by_count":11,"area":"lr"},{"id":"2605.12652","title":"Multi-Rollout On-Policy Distillation via Peer Successes and Failures","created":"2026-05-12","cited_by_count":10,"area":"distill"},{"id":"2605.22263","title":"Tailoring Teaching to Aptitude: Direction-Adaptive Self-Distillation for LLM Reasoning","created":"2026-05-21","cited_by_count":10,"area":"lr"},{"id":"2608.09867","title":"Stealing Reasoning Traces from Proprietary LLM APIs","created":"2026-08-10","cited_by_count":9,"area":"lr"},{"id":"2604.28123","title":"Beyond SFT-to-RL: Pre-alignment via Black-Box On-Policy Distillation for Multimodal RL","created":"2026-04-30","cited_by_count":8,"area":"mllm"},{"id":"2608.04419","title":"SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation","created":"2026-08-05","cited_by_count":8,"area":"distill"},{"id":"2608.16333","title":"Step-Level On-Policy Distillation: Interpolating Between On-Policy Distillation and Supervised Fine-Tuning","created":"2026-08-17","cited_by_count":8,"area":"distill"},{"id":"2604.03873","title":"SODA: Semi On-Policy Black-Box Distillation for Large Language Models","created":"2026-04-04","cited_by_count":7,"area":"distill"},{"id":"2606.01476","title":"OmniOPD: Logit-Free On-Policy Distillation via Speculative Verification","created":"2026-05-31","cited_by_count":7,"area":"lr"},{"id":"2604.07941","title":"Large Language Model Post-Training: A Unified View of Off-Policy and On-Policy Learning","created":"2026-04-09","cited_by_count":6,"area":null},{"id":"2607.28449","title":"Lightning OPD 2.0: Mitigating Style Bias in Cross-Teacher On-Policy Distillation for Large Reasoning Models","created":"2026-07-30","cited_by_count":5,"area":"lr"},{"id":"2601.22448","title":"HeaPA: Difficulty-Aware Heap Sampling and On-Policy Query Augmentation for LLM Reinforcement Learning","created":"2026-01-30","cited_by_count":4,"area":"lr"},{"id":"2605.17862","title":"$\\boldsymbol{f}$-OPD: Stabilizing Long-Horizon On-Policy Distillation with Freshness-Aware Control","created":"2026-05-18","cited_by_count":4,"area":"distill"},{"id":"2603.01683","title":"Surgical Post-Training: Proximal On-Policy Distillation for Reasoning with Knowledge Retention","created":"2026-03-02","cited_by_count":3,"area":"lr"},{"id":"2605.26105","title":"On-Policy Adversarial Flow Distillation for Autoregressive Video Generation","created":"2026-05-25","cited_by_count":3,"area":"distill"},{"id":"2606.30445","title":"When Does Online Imitation Learning Help in LLM Post-Training? The Role of (Non-)Realizability Beyond Horizon","created":"2026-06-29","cited_by_count":3,"area":"offlinerl"},{"id":"2607.04574","title":"A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training","created":"2026-07-06","cited_by_count":3,"area":"agents"},{"id":"2607.01181","title":"Right in the Right Way: LM Training with Verifiable Rewards and Human Demonstrations","created":"2026-07-01","cited_by_count":2,"area":"lr"},{"id":"2602.12155","title":"FAIL: Flow Matching Adversarial Imitation Learning for Image Generation","created":"2026-02-12","cited_by_count":1,"area":"diffusion"},{"id":"2606.07000","title":"Teaching the Way, Not the Answer: Privileged Tutoring Distillation for Multimodal Policy Optimization","created":"2026-06-05","cited_by_count":1,"area":"lr"},{"id":"2607.11505","title":"Proxy OPD: On-Policy Distillation with Transferable Relative Proxy Update","created":"2026-07-13","cited_by_count":1,"area":"distill"},{"id":"2607.20918","title":"OPOD: On-Policy Omni Distillation","created":"2026-07-23","cited_by_count":1,"area":null},{"id":"2609.36484","title":"The Teacher Is a Direction, Not a Destination: Extrapolating RL-Induced Representation Residuals in On-Policy Distillation","created":"2026-09-29","cited_by_count":1,"area":"distill"},{"id":"2609.38987","title":"Smaller Models, Better Rejects: Preference Distillation Scaling","created":"2026-09-30","cited_by_count":1,"area":"distill"},{"id":"2603.11423","title":"Beyond Single-Sample: Reliable Multi-Sample Distillation for Video Understanding","created":"2026-03-12","cited_by_count":0,"area":"mllm"},{"id":"2606.10369","title":"PADD: Path-Aligned Decompression Distillation for Non-Router Teacher to Guide MoE Student Learning","created":"2026-06-09","cited_by_count":0,"area":"moe"},{"id":"2606.16152","title":"The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2607.05346","title":"OptiAgent: End-to-End Optimization Modeling via Multi-Agent Iterative Refinement","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2607.05461","title":"AdaStop: Cost-Aware Early Stopping for DNN Test Selection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2609.07036","title":"Aha-Flow Distillation: Flow Markers Matter in LLM Reasoning","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.23449","title":"PSD: Pseudo Self-Distillation of Memory Representation Capabilities for LLM Agents","created":"2026-09-20","cited_by_count":0,"area":"agents"},{"id":"2609.29233","title":"Post-Training Leaves Behavioral Shadows on Unrelated Decisions","created":"2026-09-24","cited_by_count":0,"area":null},{"id":"2609.30864","title":"Persistent Negatives for Adversarial Black-Box On-Policy Distillation","created":"2026-09-25","cited_by_count":0,"area":"distill"},{"id":"2609.34225","title":"USA: Update-aware SAM for Cross-domain On-Policy Disitllation of Language Agents","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.34234","title":"MAS-OPD: On-Policy Distillation for Multi-agent Systems","created":"2026-09-28","cited_by_count":0,"area":"distill"},{"id":"2609.34386","title":"Look Before You Select: Rethinking Vocabulary Sparsification in On-Policy Distillation","created":"2026-09-28","cited_by_count":0,"area":"distill"},{"id":"2609.39757","title":"Revisiting On-policy Adversarial Black-Box Distillation: Calibrating Groupwise Reward Geometry for Effective Advantage Construction","created":"2026-09-30","cited_by_count":0,"area":"distill"},{"id":"2610.07247","title":"Learning What to Distill: Bilevel Top-K Token Selection for Self-Distillation in Large Language Models","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.10460","title":"Composing What Each Teacher Learned: Multi-Teacher On-Policy Distillation through Teacher-Relative Shifts","created":"2026-10-07","cited_by_count":0,"area":"distill"},{"id":"2610.14763","title":"CUSE: Fine-Grained Multimodal Unlearning with Counterfactual Guidance and On-Policy Self-Distillation","created":"2026-10-10","cited_by_count":0,"area":"mllm"},{"id":"2610.18256","title":"Teach Me After You Learn It: Lookahead Self-Distillation for RLVR","created":"2026-10-13","cited_by_count":0,"area":"distill"},{"id":"2610.19820","title":"ActionOPD: Distilling Decisions, Not Tokens","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}