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 33 / 138 页

1601. ICML 2026How RLHF Amplifies Sycophancy
1602. ICML 2026How to Train Your Advisor: Steering Black-Box LLMs with Advisor Models
1603. ICML 2026HPS: Hyperspherical Parameter Sharing for Efficient Multi-Agent Reinforcement Learning
1604. ICML 2026HTAC: Hierarchical Task-Aware Composition for Continual Offline Reinforcement Learning
1605. ICML 2026Human-in-the-Loop Policy Optimization for Preference-Based Multi-Objective Reinforcement Learning
1606. ICML 2026HumanLM: Simulating Users with State Alignment Beats Response Imitation
1607. ICML 2026Hybrid Reinforcement Learning in Adversarial Markov Decision Processes
1608. ICML 2026HyMTRL: A Hybrid Multi-Task Reinforcement Learning Framework via Phased Policy Evolution
1609. ICML 2026HyPOLE: Hyperproperty-Guided Multi-Agent Reinforcement Learning under Partial Observation
1610. ICML 2026ICR-RL: Deep Reinforcement Learning via In-Context-Regression
1611. ICML 2026Identifiable Token Correspondence for World Models
1612. ICML 2026IEC: When Information-Driven Exploration Meets Spectral Consensus via Primal–Dual Reward Regularization in Decentralized Multi-Agent RL
1613. ICML 2026iGRPO: Fast Online RL for Flow Matching Model with Instant Reward
1614. ICML 2026Imitation Learning for Multi-turn LM Agents via On-policy Expert Corrections
1615. ICML 2026Impact of Connectivity on Laplacian Representations in Reinforcement Learning
1616. ICML 2026Implicit Action Chunking for Smooth Continuous Control
1617. ICML 2026Implicit Actor Critic Coupling via a Supervised Learning Framework for RLVR
1618. ICML 2026Implicit Preference Alignment for Human Image Animation
1619. ICML 2026Implicit Safety Alignment from Crowd Preferences
1620. ICML 2026Implicit Turn-Wise Policy Optimization for Proactive User-LLM Interaction
1621. ICML 2026Improved Bounds for Reward-Agnostic and Reward-Free Exploration
1622. ICML 2026Improving Diffusion Planners by Self-Supervised Action Gating with Energies
1623. ICML 2026Improving LLM-Based Recommenders with Conservative Generative Flow Networks
1624. ICML 2026Improving Zero-Shot Offline RL via Behavioral Task Sampling
1625. ICML 2026Inference-Aware Meta-Alignment of LLMs via Non-Linear GRPO
1626. ICML 2026InfiMed-ORBIT: Aligning LLMs on Open-Ended Complex Tasks via Rubric-Based Incremental Training
1627. ICML 2026InfoDLM: an Information-Adaptive Framework for Discrete Diffusion Language Model Pretraining
1628. ICML 2026InfoPO: Information-Driven Policy Optimization for User-Centric Agents
1629. ICML 2026Informed Asymmetric Actor-Critic: Leveraging Privileged Signals Beyond Full-State Access
1630. ICML 2026InfraRL: A Benchmark for Constrained Resource Allocation in Large-Scale Infrastructure Asset Management
1631. ICML 2026InftyThink+: Effective and Efficient Infinite-Horizon Reasoning via Reinforcement Learning
1632. ICML 2026Injecting Distributional Awareness into MLLMs via Reinforcement Learning for Deep Imbalanced Regression
1633. ICML 2026Instance-Dependent Continuous-Time Reinforcement Learning via Maximum Likelihood Estimation
1634. ICML 2026Intentional Updates for Streaming Reinforcement Learning
1635. ICML 2026IntentRL: Training Proactive User-intent Agents for Open-ended Deep Research via Reinforcement Learning
1636. ICML 2026Interaction-Breaking Adversarial Learning Framework for Robust Multi-Agent Reinforcement Learning
1637. ICML 2026Internalizing Safety Understanding in Large Reasoning Models via Verification
1638. ICML 2026Interpretability Driven Evolutionary Approach for the Design of Biological Sequences
1639. ICML 2026Intrinsic Credit Assignment for Long Horizon Interaction
1640. ICML 2026Investigating Memory in Model-Free RL with POPGym Arcade
1641. ICML 2026IRPM: Intergroup Relative Preference Modeling for Pointwise Generative Reward Models
1642. ICML 2026IsoCompute Playbook: Optimally Scaling Sampling Compute for LLM RL
1643. ICML 2026Iterated Population Based Training with Task-Agnostic Restarts
1644. ICML 2026iVGR: Internalizing Visually Grounded Reasoning for MLLMs with Reinforcement Learning
1645. ICML 2026Joint-Space Empowerment as a Theory of Dexterous Motor Coordination
1646. ICML 2026Just-In-Time Reinforcement Learning: Continual Learning in LLM Agents Without Gradient Updates
1647. ICML 2026KAGE-Bench: Fast Known-Axis Visual Generalization Evaluation for Reinforcement Learning
1648. ICML 2026KBQA-R1: Reinforcing Large Language Models for Knowledge Base Question Answering
1649. ICML 2026Knapsack RL: Compute-Efficient Reinforcement Learning via Heterogeneous Rollout Allocation
1650. ICML 2026Knothe-Rosenblatt Quantile Regression for Risk-sensitive Multi-objective 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。