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 11 / 138 页

501. ICLR 2026DVLA-RL: Dual-Level Vision–Language Alignment with Reinforcement Learning Gating for Few-Shot Learning
502. ICLR 2026Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
503. ICLR 2026Dynamic Speculative Agent Planning
504. ICLR 2026Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
505. ICLR 2026Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning
506. ICLR 2026EditScore: Unlocking Online RL for Image Editing via High-Fidelity Reward Modeling
507. ICLR 2026EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget
508. ICLR 2026Efficient and Sharp Off-Policy Learning under Unobserved Confounding
509. ICLR 2026Efficient Estimation of Kernel Surrogate Models for Task Attribution
510. ICLR 2026Efficient Morphology–Control Co-Design via Stackelberg PPO under Non-Differentiable Leader–Follower Interfaces
511. ICLR 2026Efficient Offline Reinforcement Learning via Peer-Influenced Constraint
512. ICLR 2026Efficient Reinforcement Learning by Guiding World Models with Non-Curated Data
513. ICLR 2026EGG-SR: Embedding Symbolic Equivalence into Symbolic Regression via Equality Graph
514. ICLR 2026Ego-Foresight: Self-supervised Learning of Agent-Aware Representations for Improved RL
515. ICLR 2026Eliminating Inductive Bias in Reward Models with Information-Theoretic Guidance
516. ICLR 2026ELMUR: External Layer Memory with Update/Rewrite for Long-Horizon RL
517. ICLR 2026Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
518. ICLR 2026Emergence of Spatial Representation in an Actor-Critic Agent with Hippocampus-Inspired Sequence Generator
519. ICLR 2026Emergent Dexterity Via Diverse Resets and Large-Scale Reinforcement Learning
520. ICLR 2026Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
521. ICLR 2026EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion Reasoning
522. ICLR 2026Empowering LLM Tool Invocation with Tool-call Reward Model
523. ICLR 2026Empowering Multi-Robot Cooperation via Sequential World Models
524. ICLR 2026Empowering Small VLMs to Think with Dynamic Memorization and Exploration
525. ICLR 2026ENACT: Evaluating Embodied Cognition with World Modeling of Egocentric Interaction
526. ICLR 2026Enforcing Axioms for AI Alignment under Loss-Based Rules
527. ICLR 2026Enhancing Generative Auto-bidding with Offline Reward Evaluation and Policy Search
528. ICLR 2026Enhancing Geometric Perception in VLMs via Translator-Guided Reinforcement Learning
529. ICLR 2026Enhancing Language Model Reasoning with Structured Multi-Level Modeling
530. ICLR 2026Enough is as good as a feast: A Comprehensive Analysis of How Reinforcement Learning Mitigates Task Conflicts in LLMs
531. ICLR 2026Entropy Regularizing Activation: Boosting Continuous Control, Large Language Models, and Image Classification with Activation as Entropy Constraints
532. ICLR 2026Entropy-preserving reinforcement learning
533. ICLR 2026Erase to Improve: Erasable Reinforcement Learning for Search-Augmented LLMs
534. ICLR 2026ERGO: Efficient High-Resolution Visual Understanding for Vision-Language Models
535. ICLR 2026Escaping Policy Contraction: Contraction-Aware PPO (CaPPO) for Stable Language Model Fine-Tuning
536. ICLR 2026EUBRL: Epistemic Uncertainty Directed Bayesian Reinforcement Learning
537. ICLR 2026Evaluating and Improving Cultural Awareness of Reward Models for LLM Alignment
538. ICLR 2026Evaluating GFlowNet from partial episodes for stable and flexible policy-based training
539. ICLR 2026EVLP: Learning Unified Embodied Vision-Language Planner with Reinforced Supervised Fine-Tuning
540. ICLR 2026EvoTest: Evolutionary Test-Time Learning for Self-Improving Agentic Systems
541. ICLR 2026ExGRPO: Learning to Reason from Prior Successes
542. ICLR 2026Exo-Plore: Exploring Exoskeleton Control Space through Human-aligned Simulation
543. ICLR 2026Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns
544. ICLR 2026Expertise Can Be Helpful for Reinforcement Learning-based Macro Placement
545. ICLR 2026Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
546. ICLR 2026Exploratory Diffusion Model for Unsupervised Reinforcement Learning
547. ICLR 2026Exploratory Memory-Augmented LLM Agent via Hybrid On- and Off-Policy Optimization
548. ICLR 2026Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling
549. ICLR 2026EXPO: Stable Reinforcement Learning with Expressive Policies
550. ICLR 2026Fair Policy Aggregation from Standard Policy Optimization

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。