Reinforcement Learning

CodeV: Code with Images for Faithful Visual Reasoning via Tool-Aware Policy Optimization CVPR 2026 CoEvolve: Training LLM Agents via Agent-Data Mutual Evolution ACL 2026 Communication-Efficient Desire Alignment for Proactive Embodied Human–Agent Interaction ACL 2026 Conan: Progressive Learning to Reason Like a Detective over Multi-Scale Visual Evidence CVPR 2026 Consolidation or Adaptation? PRISM: Disentangling SFT and RL Data via Gradient Concentration ACL 2026 Constraint-Aware Reinforcement Learning via Adaptive Action Scaling L4DC 2026 Constructing a Japanese Rap Lyric Generation Model with GRPO ACL 2026 Controlling Multimodal Conversational Agents with Coverage-Enhanced Latent Actions ACL 2026 CoVerRL: Breaking the Consensus Trap in Label-Free Reasoning via Generator-Verifier Co-Evolution ACL 2026 CSPO: Alleviating Reward Ambiguity for Structured Table-to-LaTeX Generation ACL 2026 CURE: Critique-Driven Unified Reinforcement Learning for Test-Time Self-Improvement ACL 2026 CURE-Med: Curriculum-Informed Reinforcement Learning for Multilingual Medical Reasoning ACL 2026 D2Plan: Dual-Agent Dynamic Global Planning for Complex Retrieval-Augmented Reasoning ACL 2026 DART: Disambiguation-Aware Reasoning for Video-guided Machine Translation ACL 2026 Data Efficient RLVR via Off-Policy Influence Guidance ACL 2026 Decouple to Generalize: Context-First Self-Evolving Learning for Data-Scarce Vision-Language Reasoning CVPR 2026 Deep QP Safety Filter: Model-free Learning for Reachability-based Safety Filter L4DC 2026 Differences That Matter: Auditing Models for Capability Gap Discovery and Rectification CVPR 2026 Discovery and Reinforcement of Tool-Integrated Reasoning Chains via Rollout Trees ACL 2026 Distillation Traps and Guards: A Calibration Knob for LLM Distillability ACL 2026 Distributional Clarity: The Hidden Driver of RL-Friendliness in Large Language Models ACL 2026 DistRS: Disaggregated Reward Service for RLVR with Batch-Level Constraint NSDI 2026 DiverseGRPO: Mitigating Mode Collapse in Image Generation via Diversity-Aware GRPO CVPR 2026 Diverse Video Generation with Determinantal Point Process-Guided Policy Optimization CVPR 2026 Does RLVR Extend Reasoning Boundaries? Investigating Capability Expansion in Vision-Language Models ACL 2026