强化学习论文趋势 2023–2026

主要结论

• 强化学习论文从 2023 年的 1,070 篇增长到 2026 年的 2,985 篇，三年间扩大到约 2.8 倍。
• NeurIPS 是发强化学习论文最多的会议，2023–2026 年共 2,494 篇，占四个会议总量的 36%。
• 交叉方向里涨得最快的是推理模型：同时属于两个主题的论文从 2023 年的 9 篇增至 2026 年的 437 篇。

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

• NeurIPS 2026\texttt{FEROM}: Frontier Endogenous Reveal-Order Marginal Policy Optimization for Masked Diffusion LMs
• ICML 2026$\text{DT}^\text{2}$: Decision-Targeted Digital Twins
• ICLR 2026$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Textual Space
• CVPR 2026A Causal Marriage between VLM and IRM from Understanding to
• NeurIPS 2025$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning
• ICML 2025A Computationally Efficient Algorithm for Infinite-Horizon Average-Reward Linear MDPs
• ICLR 2025$\phi$-Update: A Class of Policy Update Methods with Policy Convergence Guarantee
• CVPR 2025All-Optical Nonlinear Diffractive Deep Network for Ultrafast Image Denoising
• NeurIPS 2024A Critical Evaluation of AI Feedback for Aligning Large Language Models
• ICML 2024${\rm E}(3)$-Equivariant Actor-Critic Methods for Cooperative Multi-Agent Reinforcement Learning
• ICLR 2024A Black-box Approach for Non-stationary Multi-agent Reinforcement Learning
• CVPR 2024DMR: Decomposed Multi-Modality Representations for Frames and Events Fusion in Visual Reinforcement Learning
• NeurIPS 2023“Why Not Looking backward?” A Robust Two-Step Method to Automatically Terminate Bayesian Optimization
• ICML 2023A Connection between One-Step RL and Critic Regularization in Reinforcement Learning
• ICLR 2023$O(T^{-1})$ Convergence of Optimistic-Follow-the-Regularized-Leader in Two-Player Zero-Sum Markov Games
• CVPR 2023"Seeing" Electric Network Frequency From Events
• NeurIPS 2026$\varphi$TD: Distributional Reinforcement Learning using Characteristic Functions
• ICML 2026$\textit{S}$-SPPO: Semantic-Calibrated Self-Play Preference Optimization
• ICLR 2026$AutoDrive\text{-}P^3$: Unified Chain of Perception–Prediction–Planning Thought via Reinforcement Fine-Tuning
• CVPR 2026AdaptVision Efficient Vision-Language Models via Adaptive Visual Acquisition

全部强化学习论文

共 911 篇，第 10 / 19 页

451. ICLR 2026Measuring and Mitigating Rapport Bias of Large Language Models under Multi-Agent Social Interactions
452. ICLR 2026Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language Models
453. ICLR 2026Mechanistic Detection and Mitigation of Hallucination in Large Reasoning Models
454. ICLR 2026MedAgentGym: A Scalable Agentic Training Environment for Code-Centric Reasoning in Biomedical Data Science
455. ICLR 2026MedVR: Annotation-Free Medical Visual Reasoning via Agentic Reinforcement Learning
456. ICLR 2026MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents
457. ICLR 2026Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents
458. ICLR 2026Memory, Benchmark & Robots: A Benchmark for Solving Complex Tasks with Reinforcement Learning
459. ICLR 2026MENLO: From Preferences to Proficiency – Evaluating and Modeling Native-like Quality Across 47 Languages
460. ICLR 2026MergeMix: A Unified Augmentation Paradigm for Visual and Multi-Modal Understanding
461. ICLR 2026Meta-RL Induces Exploration in Language Agents
462. ICLR 2026MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse
463. ICLR 2026Micro-Macro Retrieval: Reducing Long-Form Hallucination in Large Language Models
464. ICLR 2026Mini-o3: Scaling Up Reasoning Patterns and Interaction Turns for Visual Search
465. ICLR 2026Minimax Optimal Adversarial Reinforcement Learning
466. ICLR 2026MIRA: Memory-Integrated Reinforcement Learning Agent with Limited LLM Guidance
467. ICLR 2026MIRACLE: Model-free Imitation and Reinforcement Learning for Adaptive Cut-Selection
468. ICLR 2026Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions
469. ICLR 2026Mitigating Hallucination in Vision-Language Model with Depth and Spatial-aware Key-Value Refinement
470. ICLR 2026Mitigating the Safety Alignment Tax with Null-Space Constrained Policy Optimization
471. ICLR 2026Mixture-of-World Models: Scaling Multi-Task Reinforcement Learning with Modular Latent Dynamics
472. ICLR 2026MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization
473. ICLR 2026MMDuet2: Enhancing Proactive Interaction of Video MLLMs with Multi-Turn Reinforcement Learning
474. ICLR 2026MMedAgent-RL: Optimizing Multi-Agent Collaboration for Multimodal Medical Reasoning
475. ICLR 2026MobileRL: Online Agentic Reinforcement Learning for Mobile GUI Agents
476. ICLR 2026MOBODY: Model-Based Off-Dynamics Offline Reinforcement Learning
477. ICLR 2026Mode-conditioning unlocks superior test-time compute scaling
478. ICLR 2026Model Predictive Adversarial Imitation Learning for Planning from Observation
479. ICLR 2026Model-based Offline RL via Robust Value-Aware Model Learning with Implicitly Differentiable Adaptive Weighting
480. ICLR 2026MolEditRL: Structure-Preserving Molecular Editing via Discrete Diffusion and Reinforcement Learning
481. ICLR 2026MomaGraph: State-Aware Unified Scene Graphs with Vision-Language Models for Embodied Task Planning
482. ICLR 2026More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models
483. ICLR 2026Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Binding
484. ICLR 2026Multi-agent Coordination via Flow Matching
485. ICLR 2026Multi-Agent Guided Policy Optimization
486. ICLR 2026Multimodal LLM-assisted Evolutionary Search for Programmatic Control Policies
487. ICLR 2026Multimodal Policy Internalization for Conversational Agents
488. ICLR 2026Multiplayer Nash Preference Optimization
489. ICLR 2026Music Flamingo: Scaling Music Understanding in Audio Language Models
490. ICLR 2026MVR: Multi-view Video Reward Shaping for Reinforcement Learning
491. ICLR 2026Native Reasoning Models: Training Language Models to Reason on Unverifiable Data
492. ICLR 2026Near-Optimal Sample Complexity Bounds for Constrained Average-Reward MDPs
493. ICLR 2026Negotiated Reasoning: On Provably Addressing Relative Over-Generalization
494. ICLR 2026Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning
495. ICLR 2026Neural Multi-Objective Combinatorial Optimization for Flexible Job Shop Scheduling Problems
496. ICLR 2026Neural Predictor-Corrector: Solving Homotopy Problems with Reinforcement Learning
497. ICLR 2026Neural+Symbolic Approaches for Interpretable Actor-Critic Reinforcement Learning
498. ICLR 2026NFT: Bridging Supervised Learning and Reinforcement Learning in Math Reasoning
499. ICLR 2026No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers
500. ICLR 2026No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping

常见问题

2023–2026 年四大会议一共有多少篇强化学习论文？

共 6,885 篇，按年份分别是 2023 年 1,070 篇、2024 年 1,190 篇、2025 年 1,640 篇、2026 年 2,985 篇。

NeurIPS 2026 有多少篇强化学习论文？

NeurIPS 2026 有 760 篇强化学习论文，上一届是 784 篇。

ICLR 2026 有多少篇强化学习论文？

ICLR 2026 有 911 篇强化学习论文，上一届是 379 篇。

ICML 2026 有多少篇强化学习论文？

ICML 2026 有 1,021 篇强化学习论文，上一届是 405 篇。

CVPR 2026 有多少篇强化学习论文？

CVPR 2026 有 293 篇强化学习论文，上一届是 72 篇。

哪个会议的强化学习论文最多？

NeurIPS，2023–2026 年共 2,494 篇。