Reinforcement Learning

3DrawAgent: Teaching LLM to Draw in 3D with Early Contrastive Experience CVPR 2026 AAPO: Enhancing the Reasoning Capabilities of LLMs with Advantage Margin ACL 2026 Act-Adaptive Margin: Dynamically Calibrating Reward Models for Subjective Ambiguity ACL 2026 AdaDexTrack: Dynamic Modulation for Adaptive and Generalizable Dexterous Manipulation Tracking CVPR 2026 Adaptive Constraint Propagation: Scaling Structured Inference for Large Language Models via Meta-Reinforcement Learning ACL 2026 AgentGL: Towards Agentic Graph Learning with LLMs via Reinforcement Learning ACL 2026 AgenticQwen: Training Small Agentic Language Models with Dual Data Flywheels for Industrial-Scale Tool Use ACL 2026 A Goal Without a Plan Is Just a Wish: Efficient and Effective Global Planner Training for Long-Horizon Agent Task ACL 2026 ALDEN: Reinforcement Learning for Active Navigation and Evidence Gathering in Long Documents ACL 2026 Algorithm Design and Stronger Guarantees for the Improving Multi-Armed Bandits Problem UAI 2026 All Roads Lead to Rome: Incentivizing Divergent Thinking in Vision-Language Models CVPR 2026 A Model-Free Universal AI UAI 2026 Analytic Planning under Uncertainty with Moment Closure UAI 2026 Android Coach: Improve Online Agentic Training Efficiency with Single State Multiple Actions ACL 2026 An NTK Theory Approach to UCB Estimation in Semi-gradient TD Learning UAI 2026 APEX: A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal Navigation CVPR 2026 APPO: Attention-guided Perception Policy Optimization for Video Reasoning CVPR 2026 Are We Ready for RL in Text-to-3D Generation? A Progressive Investigation CVPR 2026 ARGUS: Policy-Adaptive Ad Governance via Evolving Reinforcement with Adversarial Umpiring ACL 2026 ARM-Thinker: Reinforcing Multimodal Generative Reward Models with Agentic Tool Use and Visual Reasoning CVPR 2026 A Survey of Reinforcement Learning for Large Language Models under Data Scarcity: Challenges and Solutions ACL 2026 AT²PO: Agentic Turn-based Policy Optimization via Tree Search ACL 2026 AttnPO: Attention-Guided Process Supervision for Efficient Reasoning ACL 2026 AutoGraph-R1: End-to-End Reinforcement Learning for Knowledge Graph Construction ACL 2026 AVATAR: Reinforcement Learning to See, Hear, and Reason Over Video CVPR 2026