{"total":82,"rows":[{"id":"2604.13016","title":"Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe","created":"2026-04-14","cited_by_count":299,"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":"2606.30406","title":"MOPD: Multi-Teacher On-Policy Distillation for Capability Integration in LLM Post-Training","created":"2026-06-29","cited_by_count":72,"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":"2604.24005","title":"TCOD: Exploring Temporal Curriculum in On-Policy Distillation for Multi-turn Autonomous Agents","created":"2026-04-27","cited_by_count":47,"area":"lr"},{"id":"2604.10688","title":"SCOPE: Signal-Calibrated On-Policy Distillation Enhancement with Dual-Path Adaptive Weighting","created":"2026-04-12","cited_by_count":43,"area":"lr"},{"id":"2606.02684","title":"Filter, Then Reweight: Rethinking Optimization Granularity in On-Policy Distillation","created":"2026-06-01","cited_by_count":32,"area":"lr"},{"id":"2607.14777","title":"SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning","created":"2026-07-16","cited_by_count":32,"area":"agents"},{"id":"2605.21606","title":"When Are Teacher Tokens Reliable? Position-Weighted On-Policy Self-Distillation for Reasoning","created":"2026-05-20","cited_by_count":30,"area":"distill"},{"id":"2606.01249","title":"Trust Region On-Policy Distillation","created":"2026-05-31","cited_by_count":30,"area":"distill"},{"id":"2605.07804","title":"Prune-OPD: Efficient and Reliable On-Policy Distillation for Long-Horizon Reasoning","created":"2026-05-08","cited_by_count":27,"area":"lr"},{"id":"2605.07865","title":"KL for a KL: On-Policy Distillation with Control Variate Baseline","created":"2026-05-08","cited_by_count":26,"area":"lr"},{"id":"2609.04172","title":"Rethinking On-Policy Distillation of Large Language Models II: One Training Example","created":"2026-09-03","cited_by_count":24,"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":"2605.16826","title":"Decoupling KL and Trajectories: A Unified Perspective for SFT, DAgger, Offline RL, and OPD in LLM Distillation","created":"2026-05-16","cited_by_count":20,"area":"offlinerl"},{"id":"2607.05804","title":"TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training","created":"2026-07-07","cited_by_count":17,"area":"distill"},{"id":"2605.27115","title":"Counteraction-Aware Multi-Teacher On-Policy Distillation for General Capability Recovery with Domain Preservation","created":"2026-05-26","cited_by_count":15,"area":"distill"},{"id":"2607.15161","title":"On-Policy Delta Distillation","created":"2026-07-16","cited_by_count":15,"area":"alignment"},{"id":"2605.30833","title":"Your Teacher Can't Help You Here: Combating Supervision Fidelity Decay in On-Policy Distillation","created":"2026-05-29","cited_by_count":13,"area":"lr"},{"id":"2606.30626","title":"DOPD: Dual On-policy Distillation","created":"2026-06-29","cited_by_count":12,"area":"distill"},{"id":"2606.06021","title":"OPRD: On-Policy Representation Distillation","created":"2026-06-04","cited_by_count":11,"area":"distill"},{"id":"2606.09471","title":"Escaping the KL Agreement Trap in On-Policy Distillation","created":"2026-06-08","cited_by_count":11,"area":"distill"},{"id":"2608.00782","title":"Distill Where You Fail: Recovering Learning Signals of Negative RL-Groups from Adaptive Teacher Guidance","created":"2026-08-01","cited_by_count":11,"area":"distill"},{"id":"2605.08741","title":"Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning","created":"2026-05-09","cited_by_count":10,"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":"2606.21994","title":"Prefix-Guided On-Policy Distillation: Mining Golden Trajectories from Rollouts","created":"2026-06-20","cited_by_count":10,"area":"lr"},{"id":"2608.09836","title":"Mismatch Matters: On-Policy Distillation Beyond Token Agreement","created":"2026-08-10","cited_by_count":10,"area":"distill"},{"id":"2606.17199","title":"PowerOPD: Stabilizing On-Policy Distillation with Bounded Power Transformation","created":"2026-06-15","cited_by_count":9,"area":"distill"},{"id":"2606.22830","title":"Finding the Evidence: Discovering Decision-Supporting Tokens for On-Policy Reasoning Distillation","created":"2026-06-22","cited_by_count":8,"area":"lr"},{"id":"2607.26246","title":"Weak-to-Strong On-Policy Distillation","created":"2026-07-28","cited_by_count":8,"area":"distill"},{"id":"2605.09725","title":"On-Policy Distillation with Best-of-N Teacher Rollout Selection","created":"2026-05-10","cited_by_count":7,"area":"lr"},{"id":"2606.23104","title":"ReNIO: Reweighting Negative Trajectory Importance for LLM On-Policy Distillation","created":"2026-06-22","cited_by_count":7,"area":"lr"},{"id":"2606.22793","title":"A Formula-Driven Survey and Research Agenda for On-Policy Distillation","created":"2026-06-22","cited_by_count":6,"area":"distill"},{"id":"2607.02502","title":"DemoPSD: Disagreement-Modulated Policy Self-Distillation","created":"2026-07-02","cited_by_count":6,"area":"distill"},{"id":"2608.25643","title":"A Token-Level Analysis of Sampled-Token Reverse-KL On-Policy Distillation","created":"2026-08-26","cited_by_count":6,"area":"distill"},{"id":"2609.05198","title":"What Matters in On-Policy Distillation? A Perspective on Data Efficiency and Data Selection","created":"2026-09-04","cited_by_count":6,"area":"lr"},{"id":"2607.29209","title":"SAF-OPD: Stable Advantage Fusion for On-Policy Distillation","created":"2026-07-31","cited_by_count":5,"area":"distill"},{"id":"2608.11829","title":"Towards Understanding On-Policy Distillation through the Lens of Test-Time Scaling","created":"2026-08-12","cited_by_count":5,"area":"lr"},{"id":"2608.13387","title":"CROP: Task Relevance via Counterfactuals for Selective On-Policy Distillation","created":"2026-08-13","cited_by_count":5,"area":"distill"},{"id":"2609.02998","title":"Verify Before You Distill: Prompt-Level Teacher Gating for On-Policy Distillation","created":"2026-09-02","cited_by_count":5,"area":"distill"},{"id":"2609.05295","title":"RISE: Recursive Improvement via Self-Extrapolating Policy Distillation","created":"2026-09-04","cited_by_count":5,"area":"distill"},{"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":"2605.18643","title":"Post-Trained MoE Can Skip Half Experts via Self-Distillation","created":"2026-05-18","cited_by_count":4,"area":"moe"},{"id":"2606.28562","title":"SEAD: Competence-Aware On-Policy Distillation via Entropy-Guided Supervision","created":"2026-06-26","cited_by_count":4,"area":"distill"},{"id":"2608.06802","title":"Simple-OPD: Demystifying Warm-up for On-policy Distillation","created":"2026-08-07","cited_by_count":4,"area":"distill"},{"id":"2607.04751","title":"Trust Region Policy Distillation","created":"2026-07-06","cited_by_count":3,"area":"distill"},{"id":"2607.24720","title":"The Physics of Multi-Turn Long-Horizon Planning: From Pre-training to Post-training via Single- and Multi-Teacher On-Policy Agentic Distillation","created":"2026-07-27","cited_by_count":3,"area":"wm"},{"id":"2609.15404","title":"Who Teaches Which Token? Verifier-Gated Multi-Expert On-Policy Distillation for Scientific Reasoning","created":"2026-09-14","cited_by_count":3,"area":"lr"},{"id":"2609.16937","title":"Beyond Token-Local Imitation: Reward-Compatible Temporal Credit Assignment for On-Policy Distillation","created":"2026-09-15","cited_by_count":3,"area":"distill"},{"id":"2606.00437","title":"EST-PRM: Stress-Testing Process Reward Models Before They Become Load-Bearing","created":"2026-05-30","cited_by_count":2,"area":"lr"},{"id":"2606.30345","title":"DRIFT: Difficulty Routing Self-DIstillation with Rhythm-Gated Exploration and Success BuFfer Training","created":"2026-06-29","cited_by_count":2,"area":"distill"},{"id":"2608.01735","title":"DAPD: Dual-Anchored Policy Distillation","created":"2026-08-03","cited_by_count":2,"area":null},{"id":"2609.08798","title":"Eliciting Weak-to-Strong Generalization with On-Policy Reverse Distillation","created":"2026-09-08","cited_by_count":2,"area":"distill"},{"id":"2606.03089","title":"Constitutional On-Policy Safe Distillation","created":"2026-06-02","cited_by_count":1,"area":"distill"},{"id":"2606.03620","title":"Physics-Guided Policy Optimization with Self-Distillation","created":"2026-06-02","cited_by_count":1,"area":"distill"},{"id":"2606.16733","title":"A First-Principles Derivation of LLM Policy Optimization: From Expected Reward to GRPO and Its Structural Extensions","created":"2026-06-15","cited_by_count":1,"area":"lr"},{"id":"2608.29846","title":"Influence-Directed Distillation: Solving the Diversity Bottleneck in Sampled-Token On-Policy Distillation","created":"2026-08-30","cited_by_count":1,"area":"distill"},{"id":"2610.01352","title":"MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning","created":"2026-10-01","cited_by_count":1,"area":"lr"},{"id":"2605.23954","title":"EchoDistill: Robust Large Audio Language Models via Noisy-to-Clean Self-Distillation","created":"2026-05-11","cited_by_count":0,"area":"distill"},{"id":"2607.05461","title":"AdaStop: Cost-Aware Early Stopping for DNN Test Selection","created":"2026-07-06","cited_by_count":0,"area":null},{"id":"2608.09789","title":"ADOPD: Reference-Privileged On-Policy Distillation for MLLM-Based Industrial Anomaly Detection","created":"2026-08-10","cited_by_count":0,"area":"distill"},{"id":"2608.14647","title":"SMOPD: Selective Token-Entropy Masking for Dirty-History Multi-Turn On-Policy Self-Distillation","created":"2026-07-30","cited_by_count":0,"area":"distill"},{"id":"2608.26735","title":"Recovering General Capabilities via Uncertainty-Calibrated Multi-Teacher On-Policy Distillation","created":"2026-08-27","cited_by_count":0,"area":"distill"},{"id":"2609.14708","title":"Lightning Weave: Improving the Accuracy-Efficiency Frontier of Reasoning Models through Capability Composition","created":"2026-09-13","cited_by_count":0,"area":"lr"},{"id":"2609.29142","title":"Not Every Token Is Worth Distilling: Selective Supervision for Direct-OPD","created":"2026-09-24","cited_by_count":0,"area":"distill"},{"id":"2609.32674","title":"Expected Reasoning-Step Return Unifies On-Policy Learning from Rewards and Teachers","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.32722","title":"Scaling Properties of Same-Family On-Policy Distillation","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.33200","title":"Teach Yourself Where to Look: On-Policy Attention Self-Distillation for Reasoning","created":"2026-09-27","cited_by_count":0,"area":"lr"},{"id":"2609.33409","title":"Dense Is Not Enough: Hierarchical Supervision Allocation for Long-Horizon On-Policy Distillation","created":"2026-09-27","cited_by_count":0,"area":"distill"},{"id":"2609.37377","title":"Beyond Prompt Count: How Data Shapes Transfer in On-Policy Distillation","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2609.38025","title":"Dr. OPD: Learning What to Follow for Optimal On-Policy Distillation of Large Language Models","created":"2026-09-29","cited_by_count":0,"area":"distill"},{"id":"2610.05070","title":"Outcome-Guided On-Policy Self-Distillation","created":"2026-10-04","cited_by_count":0,"area":"distill"},{"id":"2610.06105","title":"Flash-OPD: Fast On-Policy Distillation","created":"2026-10-05","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":"2610.11659","title":"DIAL-OPD: Learning More from Fewer Tokens in On-Policy Distillation","created":"2026-10-08","cited_by_count":0,"area":"distill"},{"id":"2610.11989","title":"MetaOPD: Meta-Learned Token Weighting for On-Policy Distillation","created":"2026-10-08","cited_by_count":0,"area":"distill"},{"id":"2610.13238","title":"State-OPD: State-Grounded On-Policy Distillation for Multi-Turn Agents","created":"2026-10-09","cited_by_count":0,"area":"lr"},{"id":"2610.13481","title":"Branching On-Policy Distillation","created":"2026-10-09","cited_by_count":0,"area":"distill"},{"id":"2610.14572","title":"Reward-Aligned Distillation","created":"2026-10-10","cited_by_count":0,"area":"lr"},{"id":"2610.14939","title":"VC-OPD: Visual Counterfactual On-Policy Distillation for Grounded Vision-Language Reasoning","created":"2026-10-10","cited_by_count":0,"area":"lr"},{"id":"2610.18883","title":"Token Utility for On-Policy Distillation via Local Trust-Region Optimization","created":"2026-10-01","cited_by_count":0,"area":"distill"}],"next_cursor":null}