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 784 篇，第 10 / 16 页

451. NeurIPS 2025Oryx: a Scalable Sequence Model for Many-Agent Coordination in Offline MARL
452. NeurIPS 2025OSVI-WM: One-Shot Visual Imitation for Unseen Tasks using World-Model-Guided Trajectory Generation
453. NeurIPS 2025Outcome-Based Online Reinforcement Learning: Algorithms and Fundamental Limits
454. NeurIPS 2025OWL: Optimized Workforce Learning for General Multi-Agent Assistance in Real-World Task Automation
455. NeurIPS 2025Pairwise Calibrated Rewards for Pluralistic Alignment
456. NeurIPS 2025Parameter Efficient Fine-tuning via Explained Variance Adaptation
457. NeurIPS 2025PARCO: Parallel AutoRegressive Models for Multi-Agent Combinatorial Optimization
458. NeurIPS 2025Partner Modelling Emerges in Recurrent Agents (But Only When It Matters)
459. NeurIPS 2025Pass@K Policy Optimization: Solving Harder Reinforcement Learning Problems
460. NeurIPS 2025Perception-R1: Pioneering Perception Policy with Reinforcement Learning
461. NeurIPS 2025Periodic Skill Discovery
462. NeurIPS 2025PeRL: Permutation-Enhanced Reinforcement Learning for Interleaved Vision-Language Reasoning
463. NeurIPS 2025Personalized Exercise Recommendation with Semantically-Grounded Knowledge Tracing
464. NeurIPS 2025Physics-informed Value Learner for Offline Goal-Conditioned Reinforcement Learning
465. NeurIPS 2025PhysVLM-AVR: Active Visual Reasoning for Multimodal Large Language Models in Physical Environments
466. NeurIPS 2025Pixel Reasoner: Incentivizing Pixel Space Reasoning via Curiosity-Driven Reinforcement Learning
467. NeurIPS 2025Planning and Learning in Average Risk-aware MDPs
468. NeurIPS 2025Planning with Quantized Opponent Models
469. NeurIPS 2025Planning without Search: Refining Frontier LLMs with Offline Goal-Conditioned RL
470. NeurIPS 2025Plasticity as the Mirror of Empowerment
471. NeurIPS 2025Point-RFT: Improving Multimodal Reasoning with Visually Grounded Reinforcement Finetuning
472. NeurIPS 2025PointMapPolicy: Structured Point Cloud Processing for Multi-Modal Imitation Learning
473. NeurIPS 2025Policy Compatible Skill Incremental Learning via Lazy Learning Interface
474. NeurIPS 2025Policy Gradient Methods Converge Globally in Imperfect-Information Extensive-Form Games
475. NeurIPS 2025Policy Optimized Text-to-Image Pipeline Design
476. NeurIPS 2025Praxis-VLM: Vision-Grounded Decision Making via Text-Driven Reinforcement Learning
477. NeurIPS 2025Pre-Trained Policy Discriminators are General Reward Models
478. NeurIPS 2025Predictive Coding Enhances Meta-RL To Achieve Interpretable Bayes-Optimal Belief Representation Under Partial Observability
479. NeurIPS 2025Predictive Preference Learning from Human Interventions
480. NeurIPS 2025Preference Distillation via Value based Reinforcement Learning
481. NeurIPS 2025Preference Optimization on Pareto Sets: On a Theory of Multi-Objective Optimization
482. NeurIPS 2025Preference-based Reinforcement Learning beyond Pairwise Comparisons: Benefits of Multiple Options
483. NeurIPS 2025Preference-Driven Multi-Objective Combinatorial Optimization with Conditional Computation
484. NeurIPS 2025Preserving LLM Capabilities through Calibration Data Curation: From Analysis to Optimization
485. NeurIPS 2025Pretraining a Shared Q-Network for Data-Efficient Offline Reinforcement Learning
486. NeurIPS 2025PRIMT: Preference-based Reinforcement Learning with Multimodal Feedback and Trajectory Synthesis from Foundation Models
487. NeurIPS 2025Principled Fine-tuning of LLMs from User-Edits: A Medley of Preference, Supervision, and Reward
488. NeurIPS 2025PRING: Rethinking Protein-Protein Interaction Prediction from Pairs to Graphs
489. NeurIPS 2025Prior-Guided Diffusion Planning for Offline Reinforcement Learning
490. NeurIPS 2025Probing Hidden Knowledge Holes in Unlearned LLMs
491. NeurIPS 2025Process vs. Outcome Reward: Which is Better for Agentic RAG Reinforcement Learning
492. NeurIPS 2025Progress Reward Model for Reinforcement Learning via Large Language Models
493. NeurIPS 2025Projection-based Lyapunov method for fully heterogeneous weakly-coupled MDPs
494. NeurIPS 2025Prompt Tuning Decision Transformers with Structured and Scalable Bandits
495. NeurIPS 2025Prompted Policy Search: Reinforcement Learning through Linguistic and Numerical Reasoning in LLMs
496. NeurIPS 2025ProRL: Prolonged Reinforcement Learning Expands Reasoning Boundaries in Large Language Models
497. NeurIPS 2025ProtoPairNet: Interpretable Regression through Prototypical Pair Reasoning
498. NeurIPS 2025Provable Ordering and Continuity in Vision-Language Pretraining for Generalizable Embodied Agents
499. NeurIPS 2025Provably Efficient Online RLHF with One-Pass Reward Modeling
500. NeurIPS 2025Provably Efficient RL under Episode-Wise Safety in Constrained MDPs with Linear Function Approximation

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。