{"total":51,"rows":[{"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":"2606.30626","title":"DOPD: Dual On-policy Distillation","created":"2026-06-29","cited_by_count":12,"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":"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":"2608.04419","title":"SPOT: Sparse Probing and Outcome Calibration for On-Policy Distillation","created":"2026-08-05","cited_by_count":8,"area":"distill"},{"id":"2608.08726","title":"PAST: Privileged Adaptation from Complete Student Trajectories for On-Policy Self-Distillation","created":"2026-08-09","cited_by_count":6,"area":"lr"},{"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":"2607.28449","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":"2608.03632","title":"When Teachers Mislead: Spurious-Signal-Aware On-Policy Distillation","created":"2026-08-04","cited_by_count":5,"area":"distill"},{"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":"2607.07050","title":"When Top-K Misses the Decision: Tool-Call Drift in Multi-Teacher On-Policy Distillation","created":"2026-07-08","cited_by_count":4,"area":"distill"},{"id":"2608.19181","title":"Beyond Teacher Likelihood: Group-Calibrated On-Policy Distillation for Long-Context Reasoning","created":"2026-08-19","cited_by_count":4,"area":"distill"},{"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":"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":"2605.29489","title":"Access Sets Matter: Budgeting Expert Reads for Scalable Weight-Space Model Merging","created":"2026-05-28","cited_by_count":2,"area":null},{"id":"2607.27937","title":"From Scoring to Acting: Outcome-Verified Comparative Self-Distillation for LLM Agents","created":"2026-07-30","cited_by_count":2,"area":"agents"},{"id":"2609.11699","title":"Negative Self-Distillation: Learning to Reason by Avoiding Flaws","created":"2026-09-10","cited_by_count":2,"area":"lr"},{"id":"2609.22254","title":"Teacher Should Think Ahead: Adaptive Continuations for Reliable On-Policy Distillation","created":"2026-09-06","cited_by_count":2,"area":"lr"},{"id":"2609.23697","title":"Distill What You Trust: Reliability-Aware Multi-Teacher On-Policy Distillation","created":"2026-09-20","cited_by_count":2,"area":"distill"},{"id":"2609.24432","title":"1% of Tokens Can Be Enough: On Gradient Estimation in On-Policy Distillation","created":"2026-09-21","cited_by_count":2,"area":"distill"},{"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":"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":"2608.06347","title":"RP-OPSD: Reasoning-Pivot-Guided On-Policy Self-Distillation for Multilingual Reasoning Transfer","created":"2026-08-06","cited_by_count":0,"area":"lr"},{"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":"2609.22109","title":"A Shared Learning Rate Is Not a Neutral Control in Selective On-Policy Distillation","created":"2026-08-17","cited_by_count":0,"area":"distill"},{"id":"2609.25048","title":"Teaching a Moving Student: Rethinking the Curriculum of On-Policy Distillation","created":"2026-09-06","cited_by_count":0,"area":"distill"},{"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":"2609.30837","title":"MOPD-Router: Rethinking Teacher Routing in Multi-Teacher On-Policy Distillation","created":"2026-09-25","cited_by_count":0,"area":"distill"},{"id":"2609.32333","title":"Progressive-View On-Policy Distillation for Regional-to-Global Transfer in Multimodal LLMs","created":"2026-09-26","cited_by_count":0,"area":"mllm"},{"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":"2609.32821","title":"Routing Drift Alone Does Not Diagnose Failure in Merged MoE LLMs","created":"2026-09-26","cited_by_count":0,"area":"moe"},{"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":"2609.33437","title":"SMAT: Simple and Efficient Merge-Aware Training","created":"2026-09-27","cited_by_count":0,"area":null},{"id":"2609.33455","title":"What Shared Prefixes Hide: Trajectory Dropout for On-Policy Distillation","created":"2026-09-27","cited_by_count":0,"area":"distill"},{"id":"2609.34036","title":"UOPD: Uncertainty-Aware Intervention for On-Policy Distillation of Multi-Turn Agents","created":"2026-09-27","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":"2609.34447","title":"Unbiased Top-$k$ Estimation for On-Policy Distillation","created":"2026-09-28","cited_by_count":0,"area":"distill"},{"id":"2609.35517","title":"Reward-Aligned Reweighting for On-Policy Distillation","created":"2026-09-28","cited_by_count":0,"area":"distill"},{"id":"2609.37044","title":"Learning from Think-Mode Advantage via On-Policy Distillation","created":"2026-09-29","cited_by_count":0,"area":"lr"},{"id":"2610.00979","title":"RISED: RubrIcs for agentic multi-environment Selection and sElf-Distillation","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.02678","title":"Spend Teacher Tokens Where They Matter: Success-Referenced On-Policy Distillation","created":"2026-10-02","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":"2610.08398","title":"UP-MOPD: Update Projection in Multi-Teacher On-Policy Distillation","created":"2026-10-06","cited_by_count":0,"area":"distill"},{"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":"2610.11247","title":"Why On-Policy Distillation Sometimes Fails: Vanishing Learning Signals","created":"2026-10-08","cited_by_count":0,"area":"distill"},{"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":"2610.13744","title":"A Privileged Teacher That Only Scores Cannot Search: Critique-Conditioned On-Policy Self-Distillation for Reasoning","created":"2026-10-09","cited_by_count":0,"area":"distill"},{"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"},{"id":"2610.20572","title":"Recovering Reliable Supervision via Critique-Guided On-Policy Distillation","created":"2026-10-14","cited_by_count":0,"area":"distill"}],"next_cursor":null}