{"total":48,"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":"2506.01347","title":"The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning","created":"2025-06-02","cited_by_count":162,"area":"lr"},{"id":"2507.05720","title":"MobileGUI-RL: Advancing Mobile GUI Agent through Reinforcement Learning in Online Environment","created":"2025-07-08","cited_by_count":52,"area":"lr"},{"id":"2506.18959","title":"From Web Search towards Agentic Deep Research: Incentivizing Search with Reasoning Agents","created":"2025-06-23","cited_by_count":51,"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":"2509.06283","title":"SFR-DeepResearch: Towards Effective Reinforcement Learning for Autonomously Reasoning Single Agents","created":"2025-09-08","cited_by_count":31,"area":"lr"},{"id":"2508.12800","title":"Atom-Searcher: Enhancing Agentic Deep Research via Fine-Grained Atomic Thought Reward","created":"2025-08-18","cited_by_count":25,"area":"lr"},{"id":"2505.20013","title":"WebCoT: Enhancing Web Agent Reasoning by Reconstructing Chain-of-Thought in Reflection, Branching, and Rollback","created":"2025-05-26","cited_by_count":17,"area":"lr"},{"id":"2509.22644","title":"WebGen-Agent: Enhancing Interactive Website Generation with Multi-Level Feedback and Step-Level Reinforcement Learning","created":"2025-09-26","cited_by_count":15,"area":"lr"},{"id":"2602.17665","title":"OpenEarthAgent: A Unified Framework for Tool-Augmented Geospatial Agents","created":"2026-02-19","cited_by_count":15,"area":"lr"},{"id":"2604.17073","title":"Abstain-R1: Calibrated Abstention and Post-Refusal Clarification via Verifiable RL","created":"2026-04-18","cited_by_count":14,"area":"lr"},{"id":"2512.05112","title":"DraCo: Draft as CoT for Text-to-Image Preview and Rare Concept Generation","created":"2025-12-04","cited_by_count":13,"area":"lr"},{"id":"2510.20150","title":"Rank-GRPO: Training LLM-based Conversational Recommender Systems with Reinforcement Learning","created":"2025-10-23","cited_by_count":11,"area":"lr"},{"id":"2511.02303","title":"Unlocking the Power of Multi-Agent LLM for Reasoning: From Lazy Agents to Deliberation","created":"2025-11-04","cited_by_count":11,"area":"lr"},{"id":"2601.09770","title":"GUI-Eyes: Tool-Augmented Perception for Visual Grounding in GUI Agents","created":"2026-01-14","cited_by_count":10,"area":"lr"},{"id":"2511.20718","title":"Stabilizing Off-Policy Training for Long-Horizon LLM Agent via Turn-Level Importance Sampling and Clipping-Triggered Normalization","created":"2025-11-25","cited_by_count":9,"area":"lr"},{"id":"2603.04783","title":"Breaking Contextual Inertia: Reinforcement Learning with Single-Turn Anchors for Stable Multi-Turn Interaction","created":"2026-03-05","cited_by_count":9,"area":"lr"},{"id":"2510.09577","title":"Dyna-Mind: Learning to Simulate from Experience for Better AI Agents","created":"2025-10-10","cited_by_count":8,"area":"lr"},{"id":"2602.13559","title":"OpAgent: Operator Agent for Web Navigation","created":"2026-02-14","cited_by_count":8,"area":"lr"},{"id":"2601.17699","title":"SQL-Trail: Multi-Turn Reinforcement Learning with Interleaved Feedback for Text-to-SQL","created":"2026-01-25","cited_by_count":7,"area":"lr"},{"id":"2601.21872","title":"WebArbiter: A Principle-Guided Reasoning Process Reward Model for Web Agents","created":"2026-01-29","cited_by_count":7,"area":"lr"},{"id":"2602.00528","title":"How Far Are LLMs from Professional Poker Players? Revisiting Game-Theoretic Reasoning with Agentic Tool Use","created":"2026-01-31","cited_by_count":7,"area":"lr"},{"id":"2604.02869","title":"Multi-Turn Reinforcement Learning for Tool-Calling Agents with Iterative Reward Calibration","created":"2026-04-03","cited_by_count":7,"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":"2603.08652","title":"CoCo: Code as CoT for Text-to-Image Preview and Rare Concept Generation","created":"2026-03-09","cited_by_count":6,"area":"lr"},{"id":"2603.15255","title":"SAGE: Multi-Agent Self-Evolution for LLM Reasoning","created":"2026-03-16","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":"2510.12979","title":"DeepPlanner: Scaling Planning Capability for Deep Research Agents via Advantage Shaping","created":"2025-10-14","cited_by_count":5,"area":"lr"},{"id":"2510.16252","title":"WEBSERV: A Full-Stack and RL-Ready Web Environment for Training Web Agents at Scale","created":"2025-10-17","cited_by_count":3,"area":"lr"},{"id":"2511.21638","title":"Iterative GRPO: Batch-Online Multi-Turn RL via Single-Turn RLHF","created":"2025-11-26","cited_by_count":3,"area":"lr"},{"id":"2604.07851","title":"ReRec: Reasoning-Augmented LLM-based Recommendation Assistant via Reinforcement Fine-tuning","created":"2026-04-09","cited_by_count":3,"area":"lr"},{"id":"2605.02178","title":"T$^2$PO: Uncertainty-Guided Exploration Control for Stable Multi-Turn Agentic Reinforcement Learning","created":"2026-05-04","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":"2512.18571","title":"ESearch-R1: Learning Cost-Aware MLLM Agents for Interactive Embodied Search via Reinforcement Learning","created":"2025-12-21","cited_by_count":2,"area":"lr"},{"id":"2605.07134","title":"Region4Web: Rethinking Observation Space Granularity for Web Agents","created":"2026-05-08","cited_by_count":2,"area":"lr"},{"id":"2606.05597","title":"AsyncWebRL: Efficient Asynchronous Reinforcement Learning for Multi-Step Visual Web Agents","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2606.05784","title":"TAPO: Tool-Aware Policy Optimization via Credit Transfer for Multimodal Search Agents","created":"2026-06-04","cited_by_count":2,"area":"lr"},{"id":"2510.24652","title":"Optimizing Retrieval for RAG via Reinforcement Learning","created":"2025-10-28","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":"2603.03005","title":"OrchMAS: Orchestrated Reasoning with Multi Collaborative Heterogeneous Scientific Expert Structured Agents","created":"2026-03-03","cited_by_count":0,"area":"lr"},{"id":"2603.15952","title":"Protein Design with Agent Rosetta: A Case Study for Specialized Scientific Agents","created":"2026-03-16","cited_by_count":0,"area":"lr"},{"id":"2608.00335","title":"RMSWeb: Reflection, Failure-Mode Mining, and Salvage-DS for Web Agent Reinforcement Learning","created":"2026-07-31","cited_by_count":0,"area":"lr"},{"id":"2608.26053","title":"$R^3$: Training Robots to Reason in Natural Language via Reinforcement Learning","created":"2026-08-26","cited_by_count":0,"area":"lr"},{"id":"2609.32351","title":"From Trajectories to Grounded Preferences: Process Preference Synthesis via Interaction Element Graphs for Web PRMs","created":"2026-09-26","cited_by_count":0,"area":"lr"},{"id":"2609.36178","title":"Targeting Pivotal Decisions for Credit Assignment in Agentic Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"},{"id":"2609.39021","title":"Frame Differential On-Policy Self-Distillation for Video Reasoning","created":"2026-09-30","cited_by_count":0,"area":"lr"},{"id":"2610.18683","title":"ProAS: A Progress-Aware Advantage Shaping Framework for Multi-Turn Agentic Reinforcement Learning","created":"2026-10-13","cited_by_count":0,"area":"lr"}],"next_cursor":null}