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 1,827 篇，第 1 / 37 页

1. ICLR 2026$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Textual Space
2. ICLR 2026$\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving
3. ICLR 2026$AutoDrive\text{-}P^3$: Unified Chain of Perception–Prediction–Planning Thought via Reinforcement Fine-Tuning
4. ICLR 20263D-aware Disentangled Representation for Compositional Reinforcement Learning
5. ICLR 2026A Hierarchical Circuit Symbolic Discovery Framework for Efficient Logic Optimization
6. ICLR 2026A Primer on SO(3) Action Representations in Deep Reinforcement Learning
7. ICLR 2026A Reward-Free Viewpoint on Multi-Objective Reinforcement Learning
8. ICLR 2026A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models
9. ICLR 2026A Unifying View of Coverage in Linear Off-policy Evaluation
10. ICLR 2026A$^2$Search: Ambiguity-Aware Question Answering with Reinforcement Learning
11. ICLR 2026AbstRaL: Augmenting LLMs' Reasoning by Reinforcing Abstract Thinking
12. ICLR 2026Accelerated co-design of robots through morphological pretraining
13. ICLR 2026Accelerated Learning with Linear Temporal Logic using Differentiable Simulation
14. ICLR 2026Accelerating Diffusion Planners in Offline RL via Reward-Aware Consistency Trajectory Distillation
15. ICLR 2026AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy
16. ICLR 2026Achieving Expert-Level Agent from Foundation Model via Complexity Curriculum Reinforcement Learning with Synthetic Data
17. ICLR 2026Action-Free Offline-To-Online RL via Discretised State Policies
18. ICLR 2026Activation Function Design Sustains Plasticity in Continual Learning
19. ICLR 2026Ada-Diffuser: Latent-Aware Adaptive Diffusion for Decision-Making
20. ICLR 2026Adaptive Conformal Guidance for Learning under Uncertainty
21. ICLR 2026Adaptive Rollout Allocation for Online Reinforcement Learning with Verifiable Rewards
22. ICLR 2026Adaptive Scaling of Policy Constraints for Offline Reinforcement Learning
23. ICLR 2026AdaReasoner: Dynamic Tool Orchestration for Iterative Visual Reasoning
24. ICLR 2026ADM-v2: Pursuing Full-Horizon Roll-out in Dynamics Models for Offline Policy Learning and Evaluation
25. ICLR 2026Aegis: Automated Error Generation and Identification for Multi-Agent Systems
26. ICLR 2026AesCoder: Code Aesthetics with Agentic Reward Feedback
27. ICLR 2026AgentGym-RL: An Open-Source Framework to Train LLM Agents for Long-Horizon Decision Making via Multi-Turn RL
28. ICLR 2026Agentic Jigsaw Interaction Learning for Enhancing Visual Perception and Reasoning in Vision-Language Models
29. ICLR 2026Agentic Reinforced Policy Optimization
30. ICLR 2026Agentic Reinforcement Learning with Implicit Step Rewards
31. ICLR 2026AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent
32. ICLR 2026AgentPO: Enhancing Multi-Agent Collaboration via Reinforcement Learning
33. ICLR 2026AgenTracer: Who Is Inducing Failure in the LLM Agentic Systems?
34. ICLR 2026Agnostics: Learning to Synthesize Code in Any Programming Language with a Universal Reinforcement Learning Environment
35. ICLR 2026Algorithmic Guarantees for Distilling Supervised and Offline RL Datasets
36. ICLR 2026Aligning Deep Implicit Preferences by Learning to Reason Defensively
37. ICLR 2026Alignment-Weighted DPO: A principled reasoning approach to improve alignment
38. ICLR 2026All Roads Lead to Likelihood: The Value of Reinforcement Learning in Fine-Tuning
39. ICLR 2026AlphaAgentEvo: Evolution-Oriented Alpha Mining via Self-Evolving Agentic Reinforcement Learning
40. ICLR 2026AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
41. ICLR 2026AlphaSAGE: Structure-Aware Alpha Mining via GFlowNets for Robust Exploration
42. ICLR 2026AMPED: Adaptive Multi-objective Projection for balancing Exploration and skill Diversification
43. ICLR 2026An Improved Model-free Decision-estimation Coefficient with Applications in Adversarial MDPs
44. ICLR 2026An Orthogonal Learner for Individualized Outcomes in Markov Decision Processes
45. ICLR 2026Analysis of approximate linear programming solution to Markov decision problem with log barrier function
46. ICLR 2026Anchored Supervised Fine-Tuning
47. ICLR 2026AnesSuite: A Comprehensive Benchmark and Dataset Suite for Anesthesiology Reasoning in LLMs
48. ICLR 2026APC-RL: Exceeding data-driven behavior priors with adaptive policy composition
49. ICLR 2026APPLE: Toward General Active Perception via Reinforcement Learning
50. ICLR 2026ARM-FM: Automated Reward Machines via Foundation Models for Compositional 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。