{"total":17,"rows":[{"id":"2605.15155","title":"Self-Distilled Agentic Reinforcement Learning","created":"2026-05-14","cited_by_count":55,"area":"agents"},{"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":"2606.19659","title":"SAGE-OPD: Selective Agent-Guided Intervention for Multi-Turn On-Policy Distillation","created":"2026-06-17","cited_by_count":15,"area":"agents"},{"id":"2608.05987","title":"AgentOPSD: Recursive Self-Distillation for Agentic Reinforcement Learning","created":"2026-08-06","cited_by_count":12,"area":"agents"},{"id":"2606.27814","title":"ATOD: Annealed Turn-Aware On-Policy Distillation for Multi-Turn Agentic Tasks","created":"2026-06-26","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":"2608.01837","title":"PCSD: Persistent Consistency for Self-Distillation in Agentic Reinforcement Learning","created":"2026-08-03","cited_by_count":7,"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":"2609.20784","title":"RetireOPD: Self-Retiring On-Policy Distillation for Agentic Reinforcement Learning","created":"2026-09-17","cited_by_count":3,"area":"agents"},{"id":"2608.07371","title":"Trajectory-Relative Hindsight Distillation for Agentic Reinforcement Learning","created":"2026-08-07","cited_by_count":1,"area":"agents"},{"id":"2608.09555","title":"Bidirectional Context Self-Distillation for Reinforcement Learning of Skill-Based LLM Agents","created":"2026-08-10","cited_by_count":1,"area":"agents"},{"id":"2609.14636","title":"Know When to Stop, Where to Restart: Accelerating Multi-Turn Agentic On-Policy Distillation","created":"2026-09-13","cited_by_count":1,"area":"agents"},{"id":"2609.32303","title":"Train4Merge: A Controlled Single-Teacher Study of RL vs. SFT Teachers for OPD-Based Model Merging","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.34810","title":"UniOPSD: Unifying Outcome and Hindsight Feedback for Agentic Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.36630","title":"Distilling Agentic Systems: A Roadmap across Models, Artifacts, and Harnesses","created":"2026-09-29","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":"2610.09074","title":"TAP: Efficient Long-Horizon Agent Pruning via Trajectory-Anchored Recovery","created":"2026-10-06","cited_by_count":0,"area":"agents"}],"next_cursor":null}