{"total":17,"rows":[{"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":"2608.04788","title":"Agentic Reinforcement Learning with Observation-Calibrated Self-Distillation","created":"2026-08-05","cited_by_count":7,"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":"2607.29320","title":"MAGA: Multi-Platform Self-Fusion of GUI Agents via Structured Action Distillation","created":"2026-07-31","cited_by_count":3,"area":"agents"},{"id":"2609.08919","title":"Experience Funnel: A State-Policy Alternating Loop for Self-Evolving Agents","created":"2026-09-08","cited_by_count":1,"area":"agents"},{"id":"2609.36642","title":"PR-OPD: Privileged Representation On-policy Self-Distillation for Agentic Reinforcement Learning","created":"2026-09-29","cited_by_count":1,"area":"agents"},{"id":"2609.33639","title":"Trajectory Unlearning on LLM-based Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.35058","title":"TIDE: Teacher-Student Transition via Informative Distillation and Exploration for Agentic RL","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.39436","title":"From Imitation to Reward Discovery: On-Policy Warmup for Agentic RL","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2609.40253","title":"ComputerSD: Online Self-Distillation from Real-Time Feedback for Computer-Use Agents","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.01161","title":"My FAULT: Self-Diagnosis as Credit Assignment in Self-Evolving Agentic Reinforcement Learning","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.01787","title":"Not All Experience Belongs in the Weights: Component Routing for Self-Improving GUI Agents","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"id":"2610.05303","title":"ASCENT: Online Test-Time Training of Long-Horizon Agents via Self-Distillation of Verified Experience","created":"2026-10-04","cited_by_count":0,"area":"agents"},{"id":"2610.15772","title":"RSIPO: Recursive Self-Improving Policy Optimization for Agentic Reinforcement Learning via Skill-Policy Co-Evolution","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.17953","title":"Agent-Reflex: Teaching Language Agents to Act Reflectively","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.18807","title":"SkillScaffold: Scaffolding Agentic Reinforcement Learning with Policy-Adaptive Skill Credit Assignment and Selective Injection","created":"2026-10-13","cited_by_count":0,"area":"agents"},{"id":"2610.20597","title":"Co-Evolving Acting and Forecasting for Language Agents","created":"2026-10-14","cited_by_count":0,"area":"agents"}],"next_cursor":null}