{"total":103,"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":"2604.02288","title":"Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing","created":"2026-04-02","cited_by_count":76,"area":"lr"},{"id":"2605.11182","title":"The Many Faces of On-Policy Distillation: Pitfalls, Mechanisms, and Fixes","created":"2026-05-11","cited_by_count":45,"area":"distill"},{"id":"2607.05184","title":"Rethinking On-Policy Self-Distillation for Thinking Models","created":"2026-07-06","cited_by_count":39,"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":"2607.02234","title":"Purified OPSD: On-Policy Self-Distillation Without Losing How to Think","created":"2026-07-02","cited_by_count":31,"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":"2605.07804","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":"2605.10889","title":"Unmasking On-Policy Distillation: Where It Helps, Where It Hurts, and Why","created":"2026-05-11","cited_by_count":25,"area":"lr"},{"id":"2605.13255","title":"Respecting Self-Uncertainty in On-Policy Self-Distillation for Efficient LLM Reasoning","created":"2026-05-13","cited_by_count":23,"area":"lr"},{"id":"2608.04794","title":"Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation","created":"2026-08-05","cited_by_count":18,"area":"distill"},{"id":"2605.10194","title":"STEPS: Selective On-Policy Self-Distillation for Reasoning","created":"2026-05-11","cited_by_count":16,"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":"2606.08432","title":"Trajectory-Refined Distillation","created":"2026-06-07","cited_by_count":16,"area":"distill"},{"id":"2605.10781","title":"Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR","created":"2026-05-11","cited_by_count":15,"area":"lr"},{"id":"2607.15161","title":"On-Policy Delta Distillation","created":"2026-07-16","cited_by_count":15,"area":"alignment"},{"id":"2605.11609","title":"Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information","created":"2026-05-12","cited_by_count":14,"area":"lr"},{"id":"2605.05040","title":"Preference-Based Self-Distillation: Beyond KL Matching via Reward Regularization","created":"2026-05-06","cited_by_count":12,"area":"lr"},{"id":"2605.15239","title":"Reducing the Safety Tax in LLM Safety Alignment with On-Policy Self-Distillation","created":"2026-05-14","cited_by_count":11,"area":"lr"},{"id":"2606.06021","title":"OPRD: On-Policy Representation Distillation","created":"2026-06-04","cited_by_count":11,"area":"distill"},{"id":"2605.09548","title":"Crosslingual On-Policy Self-Distillation for Multilingual Reasoning","created":"2026-05-10","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":"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":"2606.05152","title":"Reinforcement Learning from Rich Feedback with Distributional DAgger","created":"2026-06-03","cited_by_count":10,"area":"lr"},{"id":"2604.16830","title":"The Illusion of Certainty: Decoupling Capability and Calibration in On-Policy Distillation","created":"2026-04-18","cited_by_count":9,"area":"distill"},{"id":"2606.09456","title":"Breaking the Tokenizer Barrier: On-Policy Distillation across Model Families","created":"2026-06-08","cited_by_count":9,"area":"distill"},{"id":"2608.01589","title":"Is More Privileged Information Better? From Solution Traces to Problem-Solving Structure in Self-Distilled Reasoning","created":"2026-08-03","cited_by_count":9,"area":"distill"},{"id":"2608.18271","title":"Rethinking Privileged Information in On-Policy Self-Distillation","created":"2026-08-18","cited_by_count":9,"area":"distill"},{"id":"2605.12741","title":"Learning with Rare Success but Rich Feedback via Reflection-Enhanced Self-Distillation","created":"2026-05-12","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":"2605.15113","title":"Learning from Language Feedback via Variational Policy Distillation","created":"2026-05-14","cited_by_count":7,"area":"distill"},{"id":"2605.20643","title":"AVSD: Adaptive-View Self-Distillation by Balancing Consensus and Teacher-Specific Privileged Signals","created":"2026-05-20","cited_by_count":7,"area":"distill"},{"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":"2607.01763","title":"Denser $\\neq$ Better: Limits of On-Policy Self-Distillation for Continual Post-Training","created":"2026-07-02","cited_by_count":7,"area":"distill"},{"id":"2608.04788","title":"Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation","created":"2026-08-05","cited_by_count":7,"area":"agents"},{"id":"2606.15920","title":"OmniOPSD: Rationale-Privileged On-Policy Self-Distillation for Affective Computing","created":"2026-06-14","cited_by_count":6,"area":"mllm"},{"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":"2607.01480","title":"Procedural Memory Distillation: Online Reflection for Self-Improving Language Models","created":"2026-07-01","cited_by_count":6,"area":"synth"},{"id":"2607.02502","title":"DemoPSD: Disagreement-Modulated Policy Self-Distillation","created":"2026-07-02","cited_by_count":6,"area":"distill"},{"id":"2606.00959","title":"Towards Understanding Modality Interaction in Multimodal Language Models via Partial Information Decomposition","created":"2026-05-31","cited_by_count":5,"area":"mllm"},{"id":"2607.10805","title":"Diagnosing and Mitigating Thinking Collapse in On-Policy Self-Distillation","created":"2026-07-12","cited_by_count":5,"area":"lr"},{"id":"2607.18082","title":"CriPO: Enhancing Rubric-based RL via Self-Distillation","created":"2026-07-20","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":"2607.18110","title":"LLM-as-a-Coach: Experiential Learning for Non-Verifiable Tasks","created":"2026-07-20","cited_by_count":4,"area":null},{"id":"2608.06802","title":"Simple-OPD: Demystifying Warm-up for On-policy Distillation","created":"2026-08-07","cited_by_count":4,"area":"distill"},{"id":"2608.09263","title":"Privileged Likelihood Is Not Automatically Value: Three Checks for Token Credit in On-Policy Self-Distillation","created":"2026-08-10","cited_by_count":4,"area":"distill"},{"id":"2608.13179","title":"Teach the Magnitude, Not the Direction: Verifier-Bounded Credit Assignment for Multi-Turn Multi-step LLM Agents","created":"2026-08-13","cited_by_count":4,"area":"agents"},{"id":"2605.02971","title":"Multilingual Safety Alignment via Self-Distillation","created":"2026-05-03","cited_by_count":3,"area":"alignment"},{"id":"2605.16865","title":"MixSD: Mixed Contextual Self-Distillation for Knowledge Injection","created":"2026-05-16","cited_by_count":3,"area":"distill"},{"id":"2606.18216","title":"Zone of Proximal Policy Optimization: Teacher in Prompts, Not Gradients","created":"2026-06-16","cited_by_count":3,"area":"lr"},{"id":"2607.17558","title":"Why Does Feedback-Augmented Self-Distillation Fail to Improve Retrieval-Interleaved Search Agents?","created":"2026-07-20","cited_by_count":3,"area":"agents"},{"id":"2608.08176","title":"Matching Supervision to the Student's Learning Capacity: A Unified Framework for On-Policy Self-Distillation","created":"2026-08-08","cited_by_count":3,"area":"lr"},{"id":"2605.18529","title":"AMR-SD: Asymmetric Meta-Reflective Self-Distillation for Token-Level Credit Assignment","created":"2026-05-18","cited_by_count":2,"area":"lr"},{"id":"2606.03979","title":"Language Models Need Sleep: Learning to Self-Modify and Consolidate Memories","created":"2026-06-02","cited_by_count":2,"area":null},{"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":"2607.06855","title":"Geometric Self-Distillation for Reasoning Generalization","created":"2026-07-07","cited_by_count":2,"area":"lr"},{"id":"2607.28582","title":"$\\beta$-OPSD: Deriving with Policy Optimization, Training with Self-Distillation","created":"2026-07-30","cited_by_count":2,"area":"lr"},{"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":"2609.11699","title":"Negative Self-Distillation: Learning to Reason by Avoiding Flaws","created":"2026-09-10","cited_by_count":2,"area":"lr"},{"id":"2605.15532","title":"DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation","created":"2026-05-15","cited_by_count":1,"area":"lr"},{"id":"2605.30861","title":"Distilling LLM Feedback for Lean Theorem Proving","created":"2026-05-29","cited_by_count":1,"area":"lr"},{"id":"2606.02113","title":"A Primer in Post-Training Reasoning Data: What We Know About How It Works","created":"2026-06-01","cited_by_count":1,"area":"lr"},{"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":"2608.04007","title":"TurnSight: Turn-Level Hindsight Self-Distillation for Tool-Integrated Reasoning","created":"2026-08-04","cited_by_count":1,"area":"lr"},{"id":"2608.13760","title":"Amplified Does Not Mean Predictive: Reasoning Behaviors in Thinking Models","created":"2026-08-13","cited_by_count":1,"area":"lr"},{"id":"2609.21561","title":"On Repulsive and Attractive Teachers: Separating Correctness from Behavior in Self-Distillation","created":"2026-09-18","cited_by_count":1,"area":"distill"},{"id":"2609.30878","title":"TISD: On-Policy Self-Distillation with Trajectory Intervention","created":"2026-09-25","cited_by_count":1,"area":"distill"},{"id":"2610.08077","title":"Self-Retrospection Distillation: Turning Post-hoc Experiences into Prior Foresight","created":"2026-10-06","cited_by_count":1,"area":null},{"id":"2610.10447","title":"A Good Self-Teacher Meets the Student Where They Are: Joint On-Policy Learning and Teaching","created":"2026-10-07","cited_by_count":1,"area":"distill"},{"id":"2604.16158","title":"AtManRL: Towards Faithful Reasoning via Differentiable Attention Saliency","created":"2026-04-17","cited_by_count":0,"area":"lr"},{"id":"2605.14539","title":"Learning from Failures: Correction-Oriented Policy Optimization with Verifiable Rewards","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2606.17024","title":"ExpRL: Exploratory RL for LLM Mid-Training","created":"2026-06-15","cited_by_count":0,"area":"lr"},{"id":"2607.05185","title":"ClassicLogic: A Knowledge-Driven Benchmark of Classic Puzzle Games for Evaluating Compositional Generalization","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":"2608.25936","title":"One Symptom, Three Levers: A Critical Review of On-Policy Self-Distillation","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2609.03241","title":"FlowBalance: Verifier-Grounded Self-Improvement from On-Policy Reasoning Experience","created":"2026-09-03","cited_by_count":0,"area":"lr"},{"id":"2609.07036","title":"Aha-Flow Distillation: Flow Markers Matter in LLM Reasoning","created":"2026-09-07","cited_by_count":0,"area":"lr"},{"id":"2609.09957","title":"Beyond Verified Answers: Solver-Informed Self-Distillation for Bootstrapping Operations Research Language Models","created":"2026-09-09","cited_by_count":0,"area":"synth"},{"id":"2609.18805","title":"ProgramDistill: From Interactive Web Apps to Verifiable Reference-Guided SWE Tasks","created":"2026-09-16","cited_by_count":0,"area":"agents"},{"id":"2609.24646","title":"iSDFT: Information-Proximal Self-Distillation for Continual Learning in LLMs","created":"2026-09-21","cited_by_count":0,"area":"distill"},{"id":"2609.29051","title":"From Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.32201","title":"Instruct, Not Answer: Using Instruction Privileges in On-Policy Context Distillation","created":"2026-09-26","cited_by_count":0,"area":null},{"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":"2609.33335","title":"Does Learning to Predict the World Help Agents Act? Auditing World-Model Post-Training","created":"2026-09-27","cited_by_count":0,"area":"wm"},{"id":"2609.34327","title":"Knowing When Thinking Is Not Enough: Teaching Small Reasoning Models to Reason Beyond Their Parametric Knowledge","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.38792","title":"Training LLM Judges from Language Feedback via Position-Selective Self-Distillation","created":"2026-09-30","cited_by_count":0,"area":"distill"},{"id":"2609.39118","title":"Diagnosing On-Policy Self-Distillation for Reasoning Language Models","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2609.39494","title":"Disentangling Self-Distillation: Measuring and Modeling Acquisition and Retention","created":"2026-09-30","cited_by_count":0,"area":"distill"},{"id":"2610.02740","title":"Prospective Hindsight: Self-Calibrating Reinforcement Learning via Prediction-Reality Gaps","created":"2026-10-02","cited_by_count":0,"area":"deeprl"},{"id":"2610.05048","title":"E$^2$-OPSD: Taming Entropy Overshoot in On-Policy Self-Distillation","created":"2026-10-04","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":"2610.05200","title":"Learning without Overwriting: A Theory of Self-Distillation and Supervised Fine-Tuning in Continual Reasoning","created":"2026-10-04","cited_by_count":0,"area":"lr"},{"id":"2610.05872","title":"Off-Policy Merging Beats On-Policy Self-Distillation for Continual Learning","created":"2026-10-05","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":"2610.07405","title":"What pass@k Cannot Measure: Evaluating Diversity and Capability Retention after Post-Training","created":"2026-10-05","cited_by_count":0,"area":"lr"},{"id":"2610.08781","title":"IdeaAnchor: Teaching LLMs to Turn Literature into Research Ideas","created":"2026-10-06","cited_by_count":0,"area":null},{"id":"2610.16354","title":"Self-Distillation with Verbal Regularization","created":"2026-10-12","cited_by_count":0,"area":"distill"}],"next_cursor":"100"}