Methods

A Rolling Stone Gathers No Moss: Adaptive Policy Optimization for Stable Self-Evaluation in Large Multimodal Models AAAI 2026 AT²PO: Agentic Turn-based Policy Optimization via Tree Search ACL 2026 A Two-Timescale Primal-Dual Framework for Reinforcement Learning via Online Dual Variable Guidance JMLR 2026 A Unified Framework for Locality in Scalable MARL L4DC 2026 A Unified Self-Regulating Training Framework for Federated Deep Reinforcement Learning AAAI 2026 AURORA: Augmented Understanding via Structured Reasoning and Reinforcement Learning for Reference Audio-Visual Segmentation AAAI 2026 Balance Equation-based Distributionally Robust Offline Imitation Learning L4DC 2026 Balancing Signal and Variance: Adaptive Offline RL Post-Training for VLA Flow Models AAAI 2026 Bayesian Inference of Contextual Bandit Policies via Empirical Likelihood JMLR 2026 Bayesian Symbolic Regression with Entropic Reinforcement Learning UAI 2026 Behaviour Policy Optimization: Provably Lower Variance Return Estimates for Off-Policy Reinforcement Learning AAAI 2026 Benchmarking Reinforcement Learning Algorithms for ICU Ventilator Settings: An Interpretable and Probabilistic Patient Environment for Doctor Agents AAAI 2026 Best-Effort Policies for Robust Markov Decision Processes AAAI 2026 Beyond Monotonicity: Revisiting Factorization Principles in Multi-Agent Q-Learning AAAI 2026 Beyond Rule-Based Agents: Active Markov Games for Realistic Multi-Agent Interaction in Autonomous Driving CVPR 2026 Beyond Single-Speed Reasoning: Coordinating Fast and Slow Dynamics for Efficient World Modeling AAAI 2026 Beyond Single-Step Updates: Reinforcement Learning of Heuristics with Limited-Horizon Search AAAI 2026 Beyond Success: Refining Elegant Robot Manipulation from Mixed-Quality Data via Just-in-Time Intervention CVPR 2026 Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning AAAI 2026 BLM-Guard: Explainable Multimodal Ad Moderation with Chain-of-Thought and Policy-Aligned Rewards AAAI 2026 CAIC: Congestion-Aware Intent Communication for Multi-Agent Reinforcement Learning UAI 2026 Calibration-Aware Policy Optimization for Reasoning LLMs ACL 2026 CAMAR: Continuous Actions Multi-Agent Routing AAAI 2026 CAPO: A Unified Policy Gradient Approach for Reward and Cost Optimization in Safe Reinforcement Learning (Student Abstract) AAAI 2026 Causal Discovery for Efficient Offline RL with Factored Action Spaces CLeaR 2026