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 14 / 16 页

651. NeurIPS 2025STAR: Efficient Preference-based Reinforcement Learning via Dual Regularization
652. NeurIPS 2025State Entropy Regularization for Robust Reinforcement Learning
653. NeurIPS 2025State-Covering Trajectory Stitching for Diffusion Planners
654. NeurIPS 2025Steering Generative Models with Experimental Data for Protein Fitness Optimization
655. NeurIPS 2025STITCH-OPE: Trajectory Stitching with Guided Diffusion for Off-Policy Evaluation
656. NeurIPS 2025Stochastic Principal-Agent Problems: Computing and Learning Optimal History-Dependent Policies
657. NeurIPS 2025Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
658. NeurIPS 2025Strategyproof Reinforcement Learning from Human Feedback
659. NeurIPS 2025Structural Information-based Hierarchical Diffusion for Offline Reinforcement Learning
660. NeurIPS 2025Structure Matters: Dynamic Policy Gradient
661. NeurIPS 2025Structured Reinforcement Learning for Combinatorial Decision-Making
662. NeurIPS 2025Succeed or Learn Slowly: Sample Efficient Off-Policy Reinforcement Learning for Mobile App Control
663. NeurIPS 2025SURDS: Benchmarking Spatial Understanding and Reasoning in Driving Scenarios with Vision Language Models
664. NeurIPS 2025SWE-rebench: An Automated Pipeline for Task Collection and Decontaminated Evaluation of Software Engineering Agents
665. NeurIPS 2025SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
666. NeurIPS 2025SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning
667. NeurIPS 2025SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
668. NeurIPS 2025Systematic Reward Gap Optimization for Mitigating VLM Hallucinations
669. NeurIPS 2025T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
670. NeurIPS 2025Table2LaTeX-RL: High-Fidelity LaTeX Code Generation from Table Images via Reinforced Multimodal Language Models
671. NeurIPS 2025Tackling Continual Offline RL through Selective Weights Activation on Aligned Spaces
672. NeurIPS 2025Tapered Off-Policy REINFORCE - Stable and efficient reinforcement learning for large language models
673. NeurIPS 2025Teaching Language Models to Evolve with Users: Dynamic Profile Modeling for Personalized Alignment
674. NeurIPS 2025Teaching Language Models to Reason with Tools
675. NeurIPS 2025Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving
676. NeurIPS 2025Temporal Representation Alignment: Successor Features Enable Emergent Compositionality in Robot Instruction Following
677. NeurIPS 2025Temporal-Difference Variational Continual Learning
678. NeurIPS 2025TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
679. NeurIPS 2025TensorRL-QAS: Reinforcement learning with tensor networks for improved quantum architecture search
680. NeurIPS 2025Test-Time Scaling of Diffusion Models via Noise Trajectory Search
681. NeurIPS 2025Text-to-Decision Agent: Offline Meta-Reinforcement Learning from Natural Language Supervision
682. NeurIPS 2025The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training
683. NeurIPS 2025The Promise of RL for Autoregressive Image Editing
684. NeurIPS 2025The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
685. NeurIPS 2025The Unreasonable Effectiveness of Entropy Minimization in LLM Reasoning
686. NeurIPS 2025The World Is Bigger: A Computationally-Embedded Perspective on the Big World Hypothesis
687. NeurIPS 2025Think before Recommendation: Autonomous Reasoning-enhanced Recommender
688. NeurIPS 2025Think Only When You Need with Large Hybrid-Reasoning Models
689. NeurIPS 2025Think or Not? Selective Reasoning via Reinforcement Learning for Vision-Language Models
690. NeurIPS 2025Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
691. NeurIPS 2025Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
692. NeurIPS 2025Thinker: Learning to Think Fast and Slow
693. NeurIPS 2025Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction
694. NeurIPS 2025Thinkless: LLM Learns When to Think
695. NeurIPS 2025Time Reversal Symmetry for Efficient Robotic Manipulations in Deep Reinforcement Learning
696. NeurIPS 2025Time-R1: Post-Training Large Vision Language Model for Temporal Video Grounding
697. NeurIPS 2025To Distill or Decide? Understanding the Algorithmic Trade-off in Partially Observable RL
698. NeurIPS 2025To Think or Not To Think: A Study of Thinking in Rule-Based Visual Reinforcement Fine-Tuning
699. NeurIPS 2025ToolRL: Reward is All Tool Learning Needs
700. NeurIPS 2025Touch in the Wild: Learning Fine-Grained Manipulation with a Portable Visuo-Tactile Gripper

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。