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 6,885 篇，第 27 / 138 页

1301. ICML 2026Beyond the Bellman Recursion: A Pontryagin-Guided Framework for Non-Exponential Discounting
1302. ICML 2026Beyond the Proxy: Trajectory-Distilled Guidance for Offline GFlowNet Training
1303. ICML 2026Beyond Token-level Supervision: Unlocking the Potential of Decoding-based Regression via Reinforcement Learning
1304. ICML 2026Beyond Trajectory-Level Attribution: Graph-Based Credit Assignment for Agentic Reinforcement Learning
1305. ICML 2026Beyond Two-Stage Training: Cooperative SFT and RL for LLM Reasoning
1306. ICML 2026Bias in Zeroth-Order Normal Estimation for Decision-Based Attacks
1307. ICML 2026Bilevel Optimization over Saddle Points of Zero-Sum Markov Games
1308. ICML 2026BIT-LLM: Brain Instruction Tuned LLM with persistent Cross-Attention for fMRI-to-Text Decoding
1309. ICML 2026BiTrajDiff: Bidirectional Trajectory Generation with Diffusion Models for Offline Reinforcement Learning
1310. ICML 2026Black-Box Combinatorial Optimization with Order-Invariant Reinforcement Learning
1311. ICML 2026Blending Supervised and Reinforcement Fine-Tuning with Prefix Sampling
1312. ICML 2026BOOSTAPR: Boosting Automated Program Repair via Execution-Grounded Reinforcement Learning with Dual Reward Models
1313. ICML 2026Boosting CVaR Policy Optimization with Quantile Gradients
1314. ICML 2026Boosting World Models Learning via Latent-Space Value Alignment
1315. ICML 2026Bottleneck Communication Delay Minimization for Communication-Efficient Decentralized Learning
1316. ICML 2026Bottleneck-Guided Spectral Subgoals For Offline Goal-Conditioned RL
1317. ICML 2026Break the Block: Dynamic-size Reasoning Blocks for Diffusion Large Language Models via Monotonic Entropy Descent with Reinforcement Learning
1318. ICML 2026Breaking Multi-Task Curse: Reward-Weighted Evolution for Black-Box Many-Task Optimization
1319. ICML 2026Breaking the Computational Barrier: Provably Efficient Actor–Critic for Low-Rank MDPs
1320. ICML 2026Breaking the Exploration Bottleneck: Rubric-Scaffolded Reinforcement Learning for Open-Ended LLM Reasoning
1321. ICML 2026Breaking the Factorization Barrier in Diffusion Language Models
1322. ICML 2026Breaking the Self-Confirming Loop: Diagnosing and Mitigating Systemic Reward Bias in Self-Rewarding RL
1323. ICML 2026Bridging On-Device and Cloud LLMs for Collaborative Reasoning: A Unified Methodology for Local Routing and Post-Training
1324. ICML 2026Bridging the Gap Between Average and Discounted TD Learning
1325. ICML 2026Bringing Code ALIVE: Optimizing Interactive Frontend Mini-Games via Automated Play and Reinforcement Learning at Scale
1326. ICML 2026BroRL: Scaling Reinforcement Learning via Broadened Exploration
1327. ICML 2026BubbleSpec: Turning Long-Tail Bubbles into Speculative Rollout Drafts for Synchronous Reinforcement Learning
1328. ICML 2026Budget-Efficient Attacks and Robustness Training for Cooperative MARL
1329. ICML 2026CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling
1330. ICML 2026CAMEL: Confidence-Gated Reflection for Reward Modeling
1331. ICML 2026Can Agents Generalize to the Open World? Unveiling the Fragility of Static Training in Tool Use
1332. ICML 2026Can Large Language Models Generalize Procedures Across Representations?
1333. ICML 2026Can Vision Language Models Learn Intuitive Physics from Interaction?
1334. ICML 2026CaP-X: A Framework for Benchmarking and Improving Coding Agents for Robot Manipulation
1335. ICML 2026Causal Flow Q-Learning for Robust Offline Reinforcement Learning
1336. ICML 2026CausalXRL: Explainable Reinforcement Learning through Causal Graph Reasoning
1337. ICML 2026Cerebellar-Inspired Residual Control for Fault Recovery: From Inference-Time Adaptation to Structural Consolidation
1338. ICML 2026CFPO: Counterfactual Policy Optimization for Multimodal Reasoning
1339. ICML 2026Chain-of-Glimpse: Search-Guided Progressive Object-Grounded Reasoning for Video Understanding
1340. ICML 2026Chain-of-Goals Hierarchical Policy for Long-Horizon Offline Goal-Conditioned RL
1341. ICML 2026Chasing Moving Targets with Online Self-Play Reinforcement Learning for Safer Language Models
1342. ICML 2026Chebyshev Policies and the Mountain Car Problem: Reinforcement Learning for Low-Dimensional Control Tasks
1343. ICML 2026Chunk-Guided Q-Learning
1344. ICML 2026Clipped Q-Learning: Your Value Clipping Is Secretly A Robust Operator
1345. ICML 2026Clipping Bottleneck: Stabilizing RLVR via Stochastic Recovery of Near-Boundary Signals
1346. ICML 2026Clipping Low-Probability Tokens in SFT Yields a Generalizable Initialization for RL
1347. ICML 2026Closing the Sim-to-Real Gap in Non-Markovian Spreading Processes via GPU-Accelerated Distributional RL
1348. ICML 2026Co-Evolving Latent Action World Models
1349. ICML 2026CoCoEdit: Content-Consistent Image Editing via Region Regularized Reinforcement Learning
1350. ICML 2026CocoRNA: Collective RNA Design with Cooperative Multi-agent 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。