{"total":40,"rows":[{"id":"2501.17161","title":"SFT Memorizes, RL Generalizes: A Comparative Study of Foundation Model Post-training","created":"2025-01-28","cited_by_count":672,"area":"lr"},{"id":"2505.10978","title":"Group-in-Group Policy Optimization for LLM Agent Training","created":"2025-05-16","cited_by_count":497,"area":"lr"},{"id":"2408.07199","title":"Agent Q: Advanced Reasoning and Learning for Autonomous AI Agents","created":"2024-08-13","cited_by_count":208,"area":"lr"},{"id":"2509.04259","title":"RL's Razor: Why Online Reinforcement Learning Forgets Less","created":"2025-09-04","cited_by_count":176,"area":"lr"},{"id":"2507.19849","title":"Agentic Reinforced Policy Optimization","created":"2025-07-26","cited_by_count":172,"area":"lr"},{"id":"2410.02089","title":"RLEF: Grounding Code LLMs in Execution Feedback with Reinforcement Learning","created":"2024-10-02","cited_by_count":151,"area":"lr"},{"id":"2503.15478","title":"SWEET-RL: Training Multi-Turn LLM Agents on Collaborative Reasoning Tasks","created":"2025-03-19","cited_by_count":118,"area":"lr"},{"id":"2505.23678","title":"Grounded Reinforcement Learning for Visual Reasoning","created":"2025-05-29","cited_by_count":83,"area":"lr"},{"id":"2511.08567","title":"The Path Not Taken: RLVR Provably Learns Off the Principals","created":"2025-11-11","cited_by_count":56,"area":"lr"},{"id":"2506.07976","title":"Thinking vs. Doing: Agents that Reason by Scaling Test-Time Interaction","created":"2025-06-09","cited_by_count":34,"area":"lr"},{"id":"2509.12235","title":"RL Fine-Tuning Heals OOD Forgetting in SFT","created":"2025-09-08","cited_by_count":31,"area":"lr"},{"id":"2410.03524","title":"Steering Large Language Models between Code Execution and Textual Reasoning","created":"2024-10-04","cited_by_count":24,"area":"lr"},{"id":"2509.16645","title":"ADVEDM:Fine-grained Adversarial Attack against VLM-based Embodied Agents","created":"2025-09-20","cited_by_count":23,"area":"lr"},{"id":"2502.18906","title":"VEM: Environment-Free Exploration for Training GUI Agent with Value Environment Model","created":"2025-02-26","cited_by_count":19,"area":"lr"},{"id":"2503.06514","title":"GFlowVLM: Enhancing Multi-step Reasoning in Vision-Language Models with Generative Flow Networks","created":"2025-03-09","cited_by_count":15,"area":"lr"},{"id":"2505.17534","title":"Co-Reinforcement Learning for Unified Multimodal Understanding and Generation","created":"2025-05-23","cited_by_count":15,"area":"lr"},{"id":"2505.18700","title":"GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains","created":"2025-05-24","cited_by_count":14,"area":"lr"},{"id":"2511.01758","title":"RLAC: Reinforcement Learning with Adversarial Critic for Free-Form Generation Tasks","created":"2025-11-03","cited_by_count":13,"area":"lr"},{"id":"2411.00773","title":"LogiCity: Advancing Neuro-Symbolic AI with Abstract Urban Simulation","created":"2024-11-01","cited_by_count":8,"area":"lr"},{"id":"2503.15108","title":"VIPER: Visual Perception and Explainable Reasoning for Sequential Decision-Making","created":"2025-03-19","cited_by_count":8,"area":"lr"},{"id":"2504.20464","title":"A Survey on GUI Agents with Foundation Models Enhanced by Reinforcement Learning","created":"2025-04-29","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":"2503.15944","title":"From Chaos to Order: The Atomic Reasoner Framework for Fine-grained Reasoning in Large Language Models","created":"2025-03-20","cited_by_count":5,"area":"lr"},{"id":"2604.14144","title":"SpatialEvo: Self-Evolving Spatial Intelligence via Deterministic Geometric Environments","created":"2026-04-15","cited_by_count":5,"area":"lr"},{"id":"2505.16401","title":"Divide-Fuse-Conquer: Eliciting \"Aha Moments\" in Multi-Scenario Games","created":"2025-05-22","cited_by_count":4,"area":"lr"},{"id":"2505.03181","title":"VLM Q-Learning: Aligning Vision-Language Models for Interactive Decision-Making","created":"2025-05-06","cited_by_count":3,"area":"lr"},{"id":"2509.08500","title":"TCPO: Thought-Centric Preference Optimization for Effective Embodied Decision-making","created":"2025-09-10","cited_by_count":3,"area":"lr"},{"id":"2605.12620","title":"Think Twice, Act Once: Verifier-Guided Action Selection For Embodied Agents","created":"2026-05-12","cited_by_count":3,"area":"lr"},{"id":"2608.01667","title":"TCPO: Turn-Level Credit Policy Optimization","created":"2026-08-03","cited_by_count":3,"area":"lr"},{"id":"2501.18880","title":"RLS3: RL-Based Synthetic Sample Selection to Enhance Spatial Reasoning in Vision-Language Models for Indoor Autonomous Perception","created":"2025-01-31","cited_by_count":2,"area":"lr"},{"id":"2412.11391","title":"Temporal Contrastive Learning for Video Temporal Reasoning in Large Vision-Language Models","created":"2024-12-16","cited_by_count":1,"area":"lr"},{"id":"2501.08597","title":"Dynamic Knowledge Integration for Enhanced Vision-Language Reasoning","created":"2025-01-15","cited_by_count":1,"area":"lr"},{"id":"2502.10732","title":"Rule-Bottleneck Reinforcement Learning: Joint Explanation and Decision Optimization for Resource Allocation with Language Agents","created":"2025-02-15","cited_by_count":1,"area":"lr"},{"id":"2602.03547","title":"AffordanceGrasp-R1:Leveraging Reasoning-Based Affordance Segmentation with Reinforcement Learning for Robotic Grasping","created":"2026-02-03","cited_by_count":1,"area":"lr"},{"id":"2605.01882","title":"Chart-FR1: Visual Focus-Driven Fine-Grained Reasoning on Dense Charts","created":"2026-05-03","cited_by_count":1,"area":"lr"},{"id":"2606.17678","title":"See First, Answer Later: Visual Evidence Pre-Alignment via Sufficiency-Driven RL","created":"2026-06-16","cited_by_count":1,"area":"lr"},{"id":"2508.08688","title":"STELAR-VISION: Self-Topology-Aware Efficient Learning for Aligned Reasoning in Vision","created":"2025-08-12","cited_by_count":0,"area":"lr"},{"id":"2605.05407","title":"PRISM: Perception Reasoning Interleaved for Sequential Decision Making","created":"2026-05-06","cited_by_count":0,"area":"lr"},{"id":"2605.18903","title":"Reasoning Portability: Guiding Continual Learning for MLLMs in the RLVR Era","created":"2026-05-17","cited_by_count":0,"area":"lr"},{"id":"2609.35082","title":"Cross-Rollout Bellman Closure for Long-Horizon Agentic Reinforcement Learning","created":"2026-09-28","cited_by_count":0,"area":"lr"}],"next_cursor":null}