{"total":21,"rows":[{"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":"2605.01347","title":"MAD-OPD: Breaking the Ceiling in On-Policy Distillation via Multi-Agent Debate","created":"2026-05-02","cited_by_count":17,"area":"agents"},{"id":"2607.04763","title":"Multi-Turn On-Policy Distillation with Prefix Replay","created":"2026-07-06","cited_by_count":15,"area":"agents"},{"id":"2505.13820","title":"Structured Agent Distillation for Large Language Model","created":"2025-05-20","cited_by_count":13,"area":"agents"},{"id":"2606.11559","title":"HERO: Hindsight-Enhanced Reflection from Environment Observations for Agentic Self-Distillation","created":"2026-06-10","cited_by_count":11,"area":"agents"},{"id":"2608.01953","title":"Look Ahead Before You Distill: Future Trajectory Validation of Teacher Guidance for Agentic On-Policy Distillation","created":"2026-08-03","cited_by_count":11,"area":"agents"},{"id":"2608.31077","title":"Reconciling Process Supervision with Outcome-Based Credit in Agentic Policy Optimization","created":"2026-08-31","cited_by_count":4,"area":"agents"},{"id":"2607.29078","title":"DASH-OPD: Discrepancy-Aware Switching with Hysteresis for On-Policy Distillation","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2508.20324","title":"Can Compact Language Models Search Like Agents? Distillation-Guided Policy Optimization for Preserving Agentic RAG Capabilities","created":"2025-08-27","cited_by_count":2,"area":"agents"},{"id":"2607.19450","title":"REGEN: Replay-recycling for Expert-to-Generalist distillation with Offline Reinforcement Learning","created":"2026-07-21","cited_by_count":2,"area":"agents"},{"id":"2602.03022","title":"STAR: Similarity-guided Teacher-Assisted Refinement for Super-Tiny Function Calling Models","created":"2026-02-03","cited_by_count":1,"area":"agents"},{"id":"2609.39982","title":"Mid-Harness: Scaling Actions Between Model and Harness for Terminal Agents","created":"2026-09-30","cited_by_count":1,"area":"agents"},{"id":"2608.06057","title":"When History Lies: Evaluating and Improving Tool Use under Misleading Multi-Turn Histories","created":"2026-08-06","cited_by_count":0,"area":"agents"},{"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":"2609.29051","title":"From Self-Distillation to Self-Practice: Privileged Information for Multi-Turn Agents","created":"2026-09-24","cited_by_count":0,"area":"agents"},{"id":"2609.31430","title":"Compress What You See, Not What You Say: Anchored Context Distillation for Latent-Observation Software Engineering Agents","created":"2026-09-25","cited_by_count":0,"area":"agents"},{"id":"2610.02858","title":"Harness-Aware Distillation for Small Language Model Agents","created":"2026-10-02","cited_by_count":0,"area":"agents"},{"id":"2610.18424","title":"Receiver Decides Agent-to-Agent Negotiations","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.19789","title":"More Methods, Better Agents? A Reality Check on Self-Distillation in Agentic Reinforcement Learning","created":"2026-10-14","cited_by_count":0,"area":"agents"},{"id":"2610.19820","title":"ActionOPD: Distilling Decisions, Not Tokens","created":"2026-10-14","cited_by_count":0,"area":"agents"},{"id":"2610.19834","title":"Teaching Agents in their Own Style: Blackbox Teacher Distillation for Web Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}