{"total":43,"rows":[{"id":"2509.08827","title":"A Survey of Reinforcement Learning for Large Reasoning Models","created":"2025-09-10","cited_by_count":180,"area":"lr"},{"id":"2504.14239","title":"InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners","created":"2025-04-19","cited_by_count":140,"area":"lr"},{"id":"2507.05791","title":"GTA1: GUI Test-time Scaling Agent","created":"2025-07-08","cited_by_count":106,"area":"lr"},{"id":"2505.04921","title":"Perception, Reason, Think, and Plan: A Survey on Large Multimodal Reasoning Models","created":"2025-05-08","cited_by_count":90,"area":"lr"},{"id":"2505.23678","title":"Grounded Reinforcement Learning for Visual Reasoning","created":"2025-05-29","cited_by_count":83,"area":"lr"},{"id":"2505.00024","title":"Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning","created":"2025-04-25","cited_by_count":68,"area":"lr"},{"id":"2601.12538","title":"A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents","created":"2026-01-18","cited_by_count":50,"area":"lr"},{"id":"2602.22817","title":"Hierarchy-of-Groups Policy Optimization for Long-Horizon Agentic Tasks","created":"2026-02-26","cited_by_count":49,"area":"lr"},{"id":"2510.24563","title":"OSWorld-MCP: Benchmarking MCP Tool Invocation In Computer-Use Agents","created":"2025-10-28","cited_by_count":29,"area":"lr"},{"id":"2507.23779","title":"Phi-Ground Tech Report: Advancing Perception in GUI Grounding","created":"2025-07-31","cited_by_count":25,"area":"lr"},{"id":"2505.17540","title":"RePrompt: Reasoning-Augmented Reprompting for Text-to-Image Generation via Reinforcement Learning","created":"2025-05-23","cited_by_count":23,"area":"lr"},{"id":"2506.00070","title":"Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics","created":"2025-05-29","cited_by_count":21,"area":"lr"},{"id":"2508.05615","title":"Test-Time Reinforcement Learning for GUI Grounding via Region Consistency","created":"2025-08-07","cited_by_count":21,"area":"lr"},{"id":"2505.18536","title":"Reinforcement Fine-Tuning Powers Reasoning Capability of Multimodal Large Language Models","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2506.05384","title":"Q-Ponder: A Unified Training Pipeline for Reasoning-based Visual Quality Assessment","created":"2025-06-03","cited_by_count":14,"area":"lr"},{"id":"2505.15259","title":"ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search","created":"2025-05-21","cited_by_count":13,"area":"lr"},{"id":"2509.21552","title":"Learning GUI Grounding with Spatial Reasoning from Visual Feedback","created":"2025-09-25","cited_by_count":12,"area":"lr"},{"id":"2511.09127","title":"History-Aware Reasoning for GUI Agents","created":"2025-11-12","cited_by_count":11,"area":"lr"},{"id":"2601.01483","title":"Unified Generation and Self-Verification for Vision-Language Models via Advantage Decoupled Preference Optimization","created":"2026-01-04","cited_by_count":7,"area":"lr"},{"id":"2601.18631","title":"AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning","created":"2026-01-26","cited_by_count":7,"area":"lr"},{"id":"2510.27566","title":"Interact-RAG: Reason and Interact with the Corpus, Beyond Black-Box Retrieval","created":"2025-10-31","cited_by_count":6,"area":"lr"},{"id":"2603.07432","title":"Generalization in Online Reinforcement Learning for Mobile Agents","created":"2026-03-08","cited_by_count":6,"area":"lr"},{"id":"2606.02031","title":"OpenWebRL: Demystifying Online Multi-turn Reinforcement Learning for Visual Web Agents","created":"2026-06-01","cited_by_count":6,"area":"lr"},{"id":"2604.21268","title":"Measure Twice, Click Once: Co-evolving Proposer and Visual Critic via Reinforcement Learning for GUI Grounding","created":"2026-04-23","cited_by_count":5,"area":"lr"},{"id":"2508.20018","title":"SWIRL: A Staged Workflow for Interleaved Reinforcement Learning in Mobile GUI Control","created":"2025-08-27","cited_by_count":4,"area":"lr"},{"id":"2510.02204","title":"Say One Thing, Do Another? Diagnosing Reasoning-Execution Gaps in VLM-Powered Mobile-Use Agents","created":"2025-10-02","cited_by_count":4,"area":"lr"},{"id":"2603.16777","title":"Anticipatory Planning for Multimodal AI Agents","created":"2026-03-17","cited_by_count":4,"area":"lr"},{"id":"2604.06995","title":"What's Missing in Screen-to-Action? Towards a UI-in-the-Loop Paradigm for Multimodal GUI Reasoning","created":"2026-04-08","cited_by_count":4,"area":"lr"},{"id":"2510.27266","title":"Enhancing Trustworthy GUI Grounding via Self-Critiqued Reinforcement Learning","created":"2025-10-31","cited_by_count":3,"area":"lr"},{"id":"2603.21341","title":"RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models","created":"2026-03-22","cited_by_count":3,"area":"lr"},{"id":"2607.09773","title":"EvoCUA-1.5: Online Reinforcement Learning for Multi-turn Computer-Use Agents","created":"2026-07-07","cited_by_count":3,"area":"lr"},{"id":"2506.17913","title":"Learning, Reasoning, Refinement: A Framework for Kahneman's Dual-System Intelligence in GUI Agents","created":"2025-06-22","cited_by_count":2,"area":"lr"},{"id":"2509.11548","title":"How Auxiliary Reasoning Unleashes GUI Grounding in VLMs","created":"2025-09-15","cited_by_count":2,"area":"lr"},{"id":"2605.30884","title":"GUI-C$^2$: Coarse-to-Fine GUI Grounding via Difficulty-Aware Reinforcement Learning","created":"2026-05-29","cited_by_count":2,"area":"lr"},{"id":"2509.09942","title":"Towards Secure and Explainable Smart Contract Generation with Security-Aware Group Relative Policy Optimization","created":"2025-09-12","cited_by_count":1,"area":"lr"},{"id":"2511.22235","title":"Training High-Level Schedulers with Execution-Feedback Reinforcement Learning for Long-Horizon GUI Automation","created":"2025-11-27","cited_by_count":1,"area":"lr"},{"id":"2602.03084","title":"AERO: Autonomous Evolutionary Reasoning Optimization via Endogenous Dual-Loop Feedback","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2604.27859","title":"Rethinking Agentic Reinforcement Learning In Large Language Models","created":"2026-04-30","cited_by_count":1,"area":"lr"},{"id":"2511.08172","title":"An Efficient Training Pipeline for Reasoning Graphical User Interface Agents","created":"2025-11-11","cited_by_count":0,"area":"lr"},{"id":"2603.23964","title":"From Pixels to Digital Agents: An Empirical Study on the Taxonomy and Technological Trends of Reinforcement Learning Environments","created":"2026-03-25","cited_by_count":0,"area":"lr"},{"id":"2605.14311","title":"Beyond Binary: Reframing GUI Critique as Continuous Semantic Alignment","created":"2026-05-14","cited_by_count":0,"area":"lr"},{"id":"2610.10889","title":"SPLIT-RL: Staged Perception-Language Reasoning Training with Claim-Level Advantages","created":"2026-10-07","cited_by_count":0,"area":"lr"},{"id":"2610.19100","title":"GroundGUI: GUI Grounding by High-Quality Data and Distillation-to-Reinforcement Learning","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}