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 2,985 篇，第 47 / 60 页

2301. NeurIPS 2026Boosting LLM Reasoning via Human-Inspired Reward Shaping
2302. NeurIPS 2026Boosting Off-Policy RLVR with Data-Centric Replay
2303. NeurIPS 2026Bootstrapped Bipartite Actor-Critic for Diffusion RL
2304. NeurIPS 2026Breaking the Bias Barrier in Concave Multi-Objective Reinforcement Learning
2305. NeurIPS 2026Breaking the Grid: Distance-Guided Reinforcement Learning in Large Discrete Action Spaces
2306. NeurIPS 2026Breaking the Second Barrier: Sub-Second Timestamped Omni-Modal Captioning
2307. NeurIPS 2026Bridging Risk Approximation Gaps in Model Predictive Task Sampling via In-Context Modeling
2308. NeurIPS 2026Bridging Textual Profiles and Latent User Embeddings for Personalization
2309. NeurIPS 2026BSO: Safety Alignment Is Density Ratio Matching
2310. NeurIPS 2026Budgeting Discretion: Theory and Evidence on Street-Level Decision-Making
2311. NeurIPS 2026C2G-BENCH: A Cyber-Physical Evaluation Benchmark for Hierarchical Reinforcement Learning in Grid-Interactive Hyperscale Data Centers
2312. NeurIPS 2026CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating
2313. NeurIPS 2026CAFE: Causally-Guided Automated Feature Engineering with Multi-Agent Reinforcement Learning
2314. NeurIPS 2026Calibrated Safe Policy Improvement for Continuous Offline Reinforcement Learning
2315. NeurIPS 2026Calibrated Target Noise Recovers Curvature from the Gradients
2316. NeurIPS 2026Can Folding Models Tell Binders from Bluffers? Evidence from POISK: The Patent-Derived Antibody Dataset
2317. NeurIPS 2026CARD: Internalizing Expert Critique into Reinforcement Learning for Deep Search
2318. NeurIPS 2026CasePlay: Self-Play Reinforcement Learning from Case Reports for Medical Reasoning
2319. NeurIPS 2026Causal-Geo: Neuro-Symbolic Spatial Grounding for Situated Agent Planning
2320. NeurIPS 2026Certified Policy Optimisation for Nested Causal Bandits via PAC-Bayes Risk
2321. NeurIPS 2026CHAIN: Continual Heterogeneous Cooperation with Information Bottleneck for Multi-Agent Reinforcement Learning
2322. NeurIPS 2026CI4A: Semantic Component Interfaces for Agents Empowering Web Automation
2323. NeurIPS 2026CIG: Exploration via Conditional Information Gain
2324. NeurIPS 2026Clarification as Supervision: Reinforcement Learning for Vision-Language Interfaces
2325. NeurIPS 2026Clean-Label Poisoning for Gradient-Boosted Decision Trees
2326. NeurIPS 2026CLIFT: Conformal Self-Verification for Web Agent Training and Test-Time Scaling
2327. NeurIPS 2026Co-Evolving Policy Distillation
2328. NeurIPS 2026Co-GRPO: Co-Optimized Group Relative Policy Optimization for Masked Image Generation
2329. NeurIPS 2026Code2World: A GUI World Model via Renderable Code Generation
2330. NeurIPS 2026CodeScaler: Scaling Code LLM Training and Test-Time Inference via Reward Models
2331. NeurIPS 2026CoE-Agent: Co-Evolving Patient-Doctor Agents via Interactive Policy Graph Optimization for Clinical Decision Making
2332. NeurIPS 2026Cognitive Firewalls: A Synthetic Account of Cross-Lingual Reasoning Collapse
2333. NeurIPS 2026COMPASS: Composable Policy-Amortized Structured Search for LLM-Based Optimization Modeling
2334. NeurIPS 2026CompilerKV: Risk-Adaptive KV Cache Compression via Offline Experience Compilation
2335. NeurIPS 2026Compose Your Oracles: Off Policy Improvement with Aggregated Guidance
2336. NeurIPS 2026Composition-RL: Compose Your Verifiable Prompts for Reinforcement Learning of Large Language Models
2337. NeurIPS 2026Compute Aligned Training: Optimizing for Test Time Inference
2338. NeurIPS 2026Conclusions from Circuit Extraction Depend on the Level of Description: A Controlled Comparison
2339. NeurIPS 2026Conformal Selective Acting: Anytime-Valid Risk Control for RLVR-Trained LLMs
2340. NeurIPS 2026Conservatism Controllable Compositional Guidance for Offline Safe Reinforcement Learning
2341. NeurIPS 2026Conservative Pareto Set Amortization for Offline Multi-Objective Optimization
2342. NeurIPS 2026Constrained Goal-directed Planar Graph Generation with Grammar-based Reinforcement Learning
2343. NeurIPS 2026Context Value Informed In-Context Reinforcement Learning
2344. NeurIPS 2026Control First, Robustness Next: Decoupled Representation Learning for Visual RL Generalization
2345. NeurIPS 2026Controllable Molecular Generative Foundation Models
2346. NeurIPS 2026Controllable Multi-label Video Safety Detection via Adaptive Tversky Policy Optimization
2347. NeurIPS 2026Cooperative Multi-Agent Reinforcement Learning via Epigraph-Form Guided Exploration
2348. NeurIPS 2026Coordinating Hundreds of RL Agents through Scalable Inference-Time Search
2349. NeurIPS 2026Coordination Connectivity: Shared Initialization Shapes the Joint-Policy Landscape in MARL
2350. NeurIPS 2026Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation

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。