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 1,640 篇，第 31 / 33 页

1501. NeurIPS 2025SPOT: Scalable Policy Optimization with Trees for Markov Decision Processes
1502. NeurIPS 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning
1503. NeurIPS 2025SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning
1504. NeurIPS 2025Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning
1505. NeurIPS 2025Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning
1506. NeurIPS 2025STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning
1507. NeurIPS 2025STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization
1508. NeurIPS 2025State Entropy Regularization for Robust Reinforcement Learning
1509. NeurIPS 2025State-Covering Trajectory Stitching for Diffusion Planners
1510. NeurIPS 2025Steering Generative Models with Experimental Data for Protein Fitness Optimization
1511. NeurIPS 2025STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation
1512. NeurIPS 2025Stochastic Principal-Agent Problems: Computing and Learning Optimal History-Dependent Policies
1513. NeurIPS 2025Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
1514. NeurIPS 2025Strategyproof Reinforcement Learning from Human Feedback
1515. NeurIPS 2025Structural Information-based Hierarchical Diffusion for Offline Reinforcement Learning
1516. NeurIPS 2025Structure Matters: Dynamic Policy Gradient
1517. NeurIPS 2025Structured Reinforcement Learning for Combinatorial Decision-Making
1518. NeurIPS 2025Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control
1519. NeurIPS 2025SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models
1520. NeurIPS 2025SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
1521. NeurIPS 2025SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
1522. NeurIPS 2025SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning
1523. NeurIPS 2025SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
1524. NeurIPS 2025Systematic Reward Gap Optimization for Mitigating VLM Hallucinations
1525. NeurIPS 2025T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
1526. NeurIPS 2025Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models
1527. NeurIPS 2025Tackling Continual Offline RL through Selective Weights Activation on Aligned Spaces
1528. NeurIPS 2025Tapered Off-Policy REINFORCE - Stable and efficient reinforcement learning for large language models
1529. NeurIPS 2025Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
1530. NeurIPS 2025Teaching Language Models to Reason with Tools
1531. NeurIPS 2025Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
1532. NeurIPS 2025Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following
1533. NeurIPS 2025Temporal-Difference Variational Continual Learning
1534. NeurIPS 2025TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
1535. NeurIPS 2025TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture search
1536. NeurIPS 2025Test-Time Scaling of Diffusion Models via Noise Trajectory Search
1537. NeurIPS 2025Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision
1538. NeurIPS 2025The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training
1539. NeurIPS 2025The Promise of RL for Autoregressive Image Editing
1540. NeurIPS 2025The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
1541. NeurIPS 2025The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
1542. NeurIPS 2025The World Is Bigger: A Computationally-Embedded Perspective on the Big World Hypothesis
1543. NeurIPS 2025Think before Recommendation: Autonomous Reasoning-enhanced Recommender
1544. NeurIPS 2025Think Only When You Need with Large Hybrid-Reasoning Models
1545. NeurIPS 2025Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
1546. NeurIPS 2025Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
1547. NeurIPS 2025Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
1548. NeurIPS 2025Thinker: Learning to Think Fast and Slow
1549. NeurIPS 2025Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction
1550. NeurIPS 2025Thinkless: LLM Learns When to Think

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。