{"total":84,"rows":[{"id":"2603.10165","title":"OpenClaw-RL: Train Any Agent Simply by Talking","created":"2026-03-10","cited_by_count":90,"area":"agents"},{"id":"2604.10674","title":"Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents","created":"2026-04-12","cited_by_count":90,"area":"agents"},{"id":"2605.15155","title":"Self-Distilled Agentic Reinforcement Learning","created":"2026-05-14","cited_by_count":55,"area":"agents"},{"id":"2606.26790","title":"OPID: On-Policy Skill Distillation for Agentic Reinforcement Learning","created":"2026-06-25","cited_by_count":32,"area":"agents"},{"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":"2605.22166","title":"Adapting the Interface, Not the Model: Runtime Harness Adaptation for Deterministic LLM Agents","created":"2026-05-21","cited_by_count":27,"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":"2604.07430","title":"HY-Embodied-0.5: Embodied Foundation Models for Real-World Agents","created":"2026-04-08","cited_by_count":18,"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":"2603.02604","title":"Heterogeneous Agent Collaborative Reinforcement Learning","created":"2026-03-03","cited_by_count":15,"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":"2607.04763","title":"Multi-Turn On-Policy Distillation with Prefix Replay","created":"2026-07-06","cited_by_count":15,"area":"agents"},{"id":"2602.06025","title":"Learning Query-Aware Budget-Tier Routing for Runtime Agent Memory","created":"2026-02-05","cited_by_count":13,"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":"2606.11559","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":"2605.15040","title":"Orchard: An Open-Source Agentic Modeling Framework","created":"2026-05-14","cited_by_count":8,"area":"agents"},{"id":"2605.12913","title":"Revisiting DAgger in the Era of LLM-Agents","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2606.12634","title":"Keep Policy Gradient in Charge: Sibling-Guided Credit Distillation for Long-Horizon Tool-Use Agents","created":"2026-06-10","cited_by_count":6,"area":"agents"},{"id":"2606.32017","title":"TRIAGE: Role-Typed Credit Assignment for Agentic Reinforcement Learning","created":"2026-06-30","cited_by_count":6,"area":"agents"},{"id":"2607.24280","title":"From Proprietary to Open-Source: Bridging the Distribution Gap via Multi-Agent Protocol Distillation in Agentic Search","created":"2026-07-27","cited_by_count":5,"area":"agents"},{"id":"2607.10601","title":"Agentic-DPO: From Imitation to Agentic Policy Optimization on Expert Trajectories","created":"2026-07-12","cited_by_count":4,"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":"2609.08183","title":"NeoHorse-1: Towards Recursive Self-Improvement via Agentic Post-Training with Routing Harness","created":"2026-09-08","cited_by_count":4,"area":"agents"},{"id":"2607.04574","title":"A Few Teacher Steps Go a Long Way: Cost-Efficient On-Policy Data Augmentation for Agent Post-Training","created":"2026-07-06","cited_by_count":3,"area":"agents"},{"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":"2607.25308","title":"CAST: Game Solvers as Turn-Level Teachers for LLM Agents","created":"2026-07-28","cited_by_count":3,"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":"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":"2604.04651","title":"Search, Do not Guess: Teaching Small Language Models to Be Effective Search Agents","created":"2026-04-06","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":"2607.22711","title":"CORVUS: Context Optimization and Reduction Via Underlying Synchronization for LLM Coding Agents","created":"2026-07-20","cited_by_count":2,"area":"agents"},{"id":"2608.24114","title":"AHEAD: Adaptive Hindsight with Environment-Augmented Distillation for Agentic RL","created":"2026-08-25","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":"2605.29584","title":"GAPD: Gold-Action Policy Distillation for Agentic Reinforcement Learning in Knowledge Base Question Answering","created":"2026-05-28","cited_by_count":1,"area":"agents"},{"id":"2606.04484","title":"AgentJet: A Distributed Swarm Training Framework for Agentic Reinforcement Learning","created":"2026-06-03","cited_by_count":1,"area":"agents"},{"id":"2606.30044","title":"Building Multi-Task Agentic LLMs via Two-Phase Distillation","created":"2026-06-29","cited_by_count":1,"area":"agents"},{"id":"2607.17136","title":"Teach it to stop, not just to click","created":"2026-07-19","cited_by_count":1,"area":"agents"},{"id":"2607.28826","title":"Distilling Knowledge from Large Language Models into Lightweight Reinforcement Learning Agents for Autonomous Cyber Operations","created":"2026-07-30","cited_by_count":1,"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":"2608.11604","title":"Learning from Online User Feedback for Shopping Agents","created":"2026-08-12","cited_by_count":1,"area":"agents"},{"id":"2608.15763","title":"Training Agents to Evolve with Their Harness: TaoLive Digital Avatar Agent Technical Report","created":"2026-08-16","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":"2609.24526","title":"ME-VLM: A Unified VLM for Embodied Cognition and Agent Coordination","created":"2026-09-21","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":"2606.18633","title":"PersonalPlan: Planning Multi-Agent Systems for Personalized Programming Learning","created":"2026-06-17","cited_by_count":0,"area":"agents"},{"id":"2606.20002","title":"Connect the Dots: Training LLMs for Long-Lifecycle Agents with Cross-Domain Generalization Via Reinforcement Learning","created":"2026-06-18","cited_by_count":0,"area":"agents"},{"id":"2608.23911","title":"PROOF-Gen: From Optimized Data to Better Distillation","created":"2026-08-24","cited_by_count":0,"area":"agents"},{"id":"2608.25711","title":"Reassembling Distributed Risk: Trajectory-Conditioned Action Generation for Multi-Turn Agent Safety","created":"2026-08-26","cited_by_count":0,"area":"agents"},{"id":"2609.01058","title":"ARISE-RL: Agentic Rubric-Grounded Iterative Self-Evolution with Reinforcement Learning","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.04773","title":"Persistent Teacher Anchoring for Tool-Using Agents","created":"2026-09-04","cited_by_count":0,"area":"agents"},{"id":"2609.05758","title":"From Monolithic Blending to Agentic Orchestration: Dynamic Response for Conversational Assistants at Scale","created":"2026-09-04","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":"2609.25804","title":"The Tasteful Agent: Measuring and Improving Taste in Long-Horizon Tasks","created":"2026-09-22","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":"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":"2609.32520","title":"When Users Change Their Minds: Measuring and Repairing Intent Drift in LLM Agents","created":"2026-09-26","cited_by_count":0,"area":"agents"},{"id":"2609.33987","title":"Opera: A Verbal Critic Framework for Long-horizon Coding Agents","created":"2026-09-27","cited_by_count":0,"area":"agents"},{"id":"2609.34225","title":"USA: Update-aware SAM for Cross-domain On-Policy Disitllation of Language Agents","created":"2026-09-28","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":"2609.35058","title":"TIDE: Teacher-Student Transition via Informative Distillation and Exploration for Agentic RL","created":"2026-09-28","cited_by_count":0,"area":"agents"},{"id":"2609.37898","title":"Guide, Then Let Go: Gap-Adaptive Teacher Scheduling for Sparse-Reward Agentic RL","created":"2026-09-29","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":"2610.00838","title":"SHARPO: Segment-Level Credit Assignment for Agentic Reinforcement Learning","created":"2026-09-30","cited_by_count":0,"area":"agents"},{"id":"2610.00949","title":"PG-SFT: Balancing Capability Acquisition and Retention in Offline Agent Fine-Tuning","created":"2026-10-01","cited_by_count":0,"area":"agents"},{"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":"2610.01207","title":"Dependency-Aware Reward Shaping for Agentic Reinforcement Learning","created":"2026-10-01","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":"2610.05303","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":"2610.05923","title":"VERA: Scaling Verifiable Environments for Agentic co-Evolution","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.05935","title":"ThunderSyncRL: Lossless Acceleration of Agentic Reinforcement Learning","created":"2026-10-05","cited_by_count":0,"area":"agents"},{"id":"2610.12957","title":"JoyInside-VLM-Agent: Product-Conditioned Multimodal Policy Learning for Embodied Agents","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.13485","title":"Proactive Agentic Orchestration","created":"2026-10-09","cited_by_count":0,"area":"agents"},{"id":"2610.14609","title":"EviScene: Beyond \"Is It AI?\" for Agentic Image Factuality Assessment","created":"2026-10-10","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":"2610.15840","title":"LLM Value Functions for Credit Assignment in Agentic RL","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.16352","title":"A Production-Grade, High-Efficiency Agentic RL Framework for Frontier LLMs with Validated Recipes","created":"2026-10-12","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":"2610.18459","title":"Teacher-Guided Tool Learning for Small Language Models via Bidirectional KL Constraints","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}