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 13 / 16 页

601. NeurIPS 2025Scalable Exploration via Ensemble++
602. NeurIPS 2025Scalable Policy-Based RL Algorithms for POMDPs
603. NeurIPS 2025Scaling Off-Policy Reinforcement Learning with Batch and Weight Normalization
604. NeurIPS 2025Scaling Offline RL via Efficient and Expressive Shortcut Models
605. NeurIPS 2025Scaling RL to Long Videos
606. NeurIPS 2025SceneDesigner: Controllable Multi-Object Image Generation with 9-DoF Pose Manipulation
607. NeurIPS 2025Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging
608. NeurIPS 2025SE-GUI: Enhancing Visual Grounding for GUI Agents via Self-Evolutionary Reinforcement Learning
609. NeurIPS 2025Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning
610. NeurIPS 2025SEEA-R1: Tree-Structured Reinforcement Fine-Tuning for Self-Evolving Embodied Agents
611. NeurIPS 2025Seeing is Believing? Mitigating OCR Hallucinations in Multimodal Large Language Models
612. NeurIPS 2025Seeing the Arrow of Time in Large Multimodal Models
613. NeurIPS 2025Seeing through Uncertainty: Robust Task-Oriented Optimization in Visual Navigation
614. NeurIPS 2025Seg-VAR:Image Segmentation with Visual Autoregressive Modeling
615. NeurIPS 2025Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
616. NeurIPS 2025Self-Adapting Language Models
617. NeurIPS 2025Self-Challenging Language Model Agents
618. NeurIPS 2025Self-Guided Hierarchical Exploration for Generalist Foundation Model Web Agents
619. NeurIPS 2025Self-Improving Embodied Foundation Models
620. NeurIPS 2025Self-Verifying Reflection Helps Transformers with CoT Reasoning
621. NeurIPS 2025Selftok-Zero: Reinforcement Learning for Visual Generation via Discrete and Autoregressive Visual Tokens
622. NeurIPS 2025Semantic-guided Diverse Decoding for Large Language Model
623. NeurIPS 2025Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning
624. NeurIPS 2025Sequential Attention-based Sampling for Histopathological Analysis
625. NeurIPS 2025Sequential Monte Carlo for Policy Optimization in Continuous POMDPs
626. NeurIPS 2025Sequential Multi-Agent Dynamic Algorithm Configuration
627. NeurIPS 2025SeRL: Self-play Reinforcement Learning for Large Language Models with Limited Data
628. NeurIPS 2025Sharp Analysis for KL-Regularized Contextual Bandits and RLHF
629. NeurIPS 2025Sharp Gap-Dependent Variance-Aware Regret Bounds for Tabular MDPs
630. NeurIPS 2025Shift Before You Learn: Enabling Low-Rank Representations in Reinforcement Learning
631. NeurIPS 2025ShiQ: Bringing back Bellman to LLMs
632. NeurIPS 2025ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning
633. NeurIPS 2025Simultaneous Statistical Inference for Off-Policy Evaluation in Reinforcement Learning
634. NeurIPS 2025Skill-Driven Neurosymbolic State Abstractions
635. NeurIPS 2025Social World Model-Augmented Mechanism Design Policy Learning
636. NeurIPS 2025Solver-Informed RL: Grounding Large Language Models for Authentic Optimization Modeling
637. NeurIPS 2025Solving Continuous Mean Field Games: Deep Reinforcement Learning for Non-Stationary Dynamics
638. NeurIPS 2025SOMBRL: Scalable and Optimistic Model-Based RL
639. NeurIPS 2025SonoGym: High Performance Simulation for Challenging Surgical Tasks with Robotic Ultrasound
640. NeurIPS 2025SORTeD Rashomon Sets of Sparse Decision Trees: Anytime Enumeration
641. NeurIPS 2025Spatial-Aware Decision-Making with Ring Attractors in Reinforcement Learning Systems
642. NeurIPS 2025SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning
643. NeurIPS 2025Spectral Learning for Infinite-Horizon Average-Reward POMDPs
644. NeurIPS 2025SPiDR: A Simple Approach for Zero-Shot Safety in Sim-to-Real Transfer
645. NeurIPS 2025SPOT: Scalable Policy Optimization with Trees for Markov Decision Processes
646. NeurIPS 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning
647. NeurIPS 2025SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning
648. NeurIPS 2025Stable Gradients for Stable Learning at Scale in Deep Reinforcement Learning
649. NeurIPS 2025Staggered Environment Resets Improve Massively Parallel On-Policy Reinforcement Learning
650. NeurIPS 2025STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning

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。