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 1,021 篇，第 20 / 21 页

951. ICML 2026Trojan-Speak: Bypassing Constitutional Classifiers with No Jailbreak Tax via Adversarial Finetuning
952. ICML 2026Trust Region Inverse Reinforcement Learning: Explicit Dual Ascent using Local Policy Updates
953. ICML 2026Trust Region Masking for Long-Horizon LLM Reinforcement Learning
954. ICML 2026Trust-Region Diffusion Policies for Massively Parallel On-Policy RL
955. ICML 2026TruthRL: Incentivizing Truthful LLMs via Reinforcement Learning
956. ICML 2026TUR-DPO: Topology- and Uncertainty-Aware Direct Preference Optimization
957. ICML 2026Tvcache: A Tool-Value Cache for Post-Training LLM Agents
958. ICML 2026Twice Sequential Monte Carlo for Tree Search
959. ICML 2026UAV$^2$: A Unified and Adaptive Scheduling Framework for UAV Autopilot System with Reinforcement Learning
960. ICML 2026UCPO: Uncertainty-Aware Policy Optimization
961. ICML 2026UDM-GRPO: Stable and Efficient Group Relative Policy Optimization for Uniform Discrete Diffusion Models
962. ICML 2026UGround: Towards Unified Visual Grounding with Unrolled Transformers
963. ICML 2026UI2Code^N: UI-to-Code Generation as Interactive Visual Optimization
964. ICML 2026Unbiased Alignment for Large Language Models with Noisy Preferences
965. ICML 2026Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization
966. ICML 2026Unbiased Principles, Robust Rewards
967. ICML 2026Unbiased Reward Modeling from Implicit Feedback for LLM Alignment
968. ICML 2026Uncertainty-Guided Exploration and Stable Planning for Sparse-Reward Manipulation from Limited Demonstrations
969. ICML 2026Understanding the Performance Gap in Preference Learning: A Dichotomy of RLHF and DPO
970. ICML 2026Unified Multimodal Autoregressive Modeling with Shared Context—Visual Tokenizer is Key to Unification
971. ICML 2026Unifying and Optimizing Data Values for Selection via Sequential Decision-Making
972. ICML 2026Unifying Stacking and Cascading for Efficient Ensemble Inference
973. ICML 2026Unifying Value Alignment and Assignment in Cross-Domain Offline Reinforcement Learning with Heterogeneous Datasets
974. ICML 2026UniRRM: Unified Reasoning Reward Models Across Languages and Evaluation Paradigms
975. ICML 2026Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs
976. ICML 2026Unleashing Implicit Rewards: Prefix-Value Learning for Distribution-Level Optimization
977. ICML 2026Unlocking Zero-Shot Geospatial Reasoning via Indirect Rewards
978. ICML 2026Unsupervised Hierarchical Skill Discovery
979. ICML 2026Unsupervised Partner Design Enables Robust Ad-hoc Teamwork
980. ICML 2026V1: Unifying Generation and Self-Verification for Parallel Reasoners
981. ICML 2026Value Aggregation with Uncertainty in Online Decentralized MARL
982. ICML 2026Value-as-Return: A Two-Stage Framework to Align on the Optimal Score Function
983. ICML 2026VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
984. ICML 2026Variance Driven Exploration: A Provable and Efficient Methodology for Pure Exploration in Highly Stochastic Environments
985. ICML 2026VeriSimpl: Robust Optimization Modeling from Natural Language using Simplification-based Verification
986. ICML 2026VeRO: A Harness for Agents to Optimize Agents
987. ICML 2026Video-Based Optimal Transport for Feedback-Efficient Offline Preference-Based Reinforcement Learning
988. ICML 2026Video-o3: Native Interleaved Clue Seeking for Long Video Multi-Hop Reasoning
989. ICML 2026Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation
990. ICML 2026VideoGPA: Distilling Geometry Priors for 3D-Consistent Video Generation
991. ICML 2026VideoSEG-O3: A Multi-turn Reinforcement Learning Framework for Reasoning Video Object Segmentation
992. ICML 2026VideoTemp-o3: Harmonizing Temporal Grounding and Video Understanding in Agentic Thinking-with-Videos
993. ICML 2026VideoTrace-R1: Long Video-based Retrieval-Augmented Generation via Reinforcement Learning
994. ICML 2026VideoVeritas: AI-Generated Video Detection via Perception Pretext Reinforcement Learning
995. ICML 2026VIPO: Value Function Inconsistency Penalized Offline Reinforcement Learning
996. ICML 2026VisualScore: Learning Holistic Visual Quality Scores via Multi-Task Reasoning
997. ICML 2026ViSurf: Visual Supervised-and-Reinforcement Fine-Tuning for Large Vision-and-Language Models
998. ICML 2026Vulnerable Agent Identification in Large-Scale Multi-Agent Reinforcement Learning
999. ICML 2026Well-Posed KL-Regularized Control via Wasserstein and Kalman–Wasserstein KL Divergences
1000. ICML 2026What Does Flow-Matching Bring to TD-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。