{"total":33,"rows":[{"id":"2509.02547","title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","created":"2025-09-02","cited_by_count":205,"area":"agents"},{"id":"2509.18119","title":"MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents","created":"2025-09-10","cited_by_count":43,"area":"agents"},{"id":"2605.26684","title":"Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning","created":"2026-05-26","cited_by_count":31,"area":"agents"},{"id":"2509.07553","title":"VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents","created":"2025-09-09","cited_by_count":15,"area":"agents"},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"id":"2604.11784","title":"ClawGUI: A Unified Framework for Training, Evaluating, and Deploying GUI Agents","created":"2026-04-13","cited_by_count":14,"area":"agents"},{"id":"2602.11524","title":"Adaptive Milestone Reward for GUI Agents","created":"2026-02-12","cited_by_count":12,"area":"agents"},{"id":"2606.20683","title":"From Question Answering to Task Completion: A Survey on Agent System and Harness Design","created":"2026-06-14","cited_by_count":12,"area":"agents"},{"id":"2605.00642","title":"Learn where to Click from Yourself: On-Policy Self-Distillation for GUI Grounding","created":"2026-05-01","cited_by_count":11,"area":"agents"},{"id":"2603.19191","title":"OS-Themis: A Scalable Critic Framework for Generalist GUI Rewards","created":"2026-03-19","cited_by_count":10,"area":"agents"},{"id":"2509.11067","title":"Agentic Lybic: Multi-Agent Execution System with Tiered Reasoning and Orchestration","created":"2025-09-14","cited_by_count":8,"area":"agents"},{"id":"2606.12191","title":"Agentic Environment Engineering for Large Language Models: A Survey of Environment Modeling, Synthesis, Evaluation, and Application","created":"2026-06-10","cited_by_count":8,"area":"agents"},{"id":"2607.04425","title":"UI-MOPD: Multi-Platform On-Policy Distillation for Unified GUI Agents","created":"2026-07-05","cited_by_count":8,"area":"agents"},{"id":"2509.26506","title":"SCUBA: Salesforce Computer Use Benchmark","created":"2025-09-30","cited_by_count":7,"area":"agents"},{"id":"2606.26027","title":"Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It","created":"2026-06-24","cited_by_count":7,"area":"agents"},{"id":"2607.11185","title":"SCALECUA: Scaling Computer Use Agents with Verifiable Task Synthesis and Efficient Online RL","created":"2026-07-13","cited_by_count":7,"area":"agents"},{"id":"2602.10356","title":"Autonomous Continual Learning for Environment Adaptation of Computer-Use Agents","created":"2026-02-10","cited_by_count":6,"area":"agents"},{"id":"2510.04607","title":"From Imperative to Declarative: Towards LLM-friendly OS Interfaces for Boosted Computer-Use Agents","created":"2025-10-06","cited_by_count":4,"area":"agents"},{"id":"2606.23049","title":"PhoneBuddy: Training Open Models for Agentic Phone Use","created":"2026-06-22","cited_by_count":4,"area":"agents"},{"id":"2607.24112","title":"Scaling GUI Agents with Visual State Transitions","created":"2026-07-27","cited_by_count":4,"area":"agents"},{"id":"2604.27955","title":"GUI Agents with Reinforcement Learning: Toward Digital Inhabitants","created":"2026-04-30","cited_by_count":3,"area":"agents"},{"id":"2607.25904","title":"Interactive Reward Agent: GUI Task Evaluation via Environment-State Verification","created":"2026-07-28","cited_by_count":3,"area":"agents"},{"id":"2606.18890","title":"Skill-Guided Continuation Distillation for GUI Agents","created":"2026-06-17","cited_by_count":2,"area":"agents"},{"id":"2605.15565","title":"AstraFlow: Dataflow-Oriented Reinforcement Learning for Agentic LLMs","created":"2026-05-15","cited_by_count":1,"area":"agents"},{"id":"2606.24515","title":"Reinforcement Learning for Computer-Use Agents with Autonomous Evaluation","created":"2026-06-23","cited_by_count":1,"area":"agents"},{"id":"2510.27140","title":"Measuring the Security of Mobile LLM Agents under Adversarial Prompts from Untrusted Third-Party Channels","created":"2025-10-31","cited_by_count":0,"area":"agents"},{"id":"2602.17245","title":"Web Agents Should Use Typed Actions Instead of Click-Based Browsing","created":"2026-02-19","cited_by_count":0,"area":"agents"},{"id":"2606.29705","title":"GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots","created":"2026-06-29","cited_by_count":0,"area":"agents"},{"id":"2608.06862","title":"SynChain: Inducing Computer-Use Agent Systems to Construct Their Own Attack Chains","created":"2026-08-07","cited_by_count":0,"area":"agents"},{"id":"2608.25777","title":"LocalLSTC: A Long Short-Term Control Architecture for Locally Deployed GUI Agents","created":"2026-08-26","cited_by_count":0,"area":"agents"},{"id":"2609.22178","title":"Beyond Task Completion: Training Capable and Safe Computer-Use Agents","created":"2026-08-27","cited_by_count":0,"area":"agents"},{"id":"2609.27307","title":"Learn How to Act from Your Own Interactions: On-Policy Self-Distillation for GUI Agents","created":"2026-09-23","cited_by_count":0,"area":"agents"},{"id":"2609.38008","title":"HybridCUA: Learning to Orchestrate GUI and CLI for Computer-Use Agents","created":"2026-09-29","cited_by_count":0,"area":"agents"}],"next_cursor":null}