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 1,190 篇，第 16 / 24 页

751. NeurIPS 2024Adversarially Robust Decision Transformer
752. NeurIPS 2024Adversarially Trained Weighted Actor-Critic for Safe Offline Reinforcement Learning
753. NeurIPS 2024AGILE: A Novel Reinforcement Learning Framework of LLM Agents
754. NeurIPS 2024Aligner: Efficient Alignment by Learning to Correct
755. NeurIPS 2024Aligning Diffusion Behaviors with Q-functions for Efficient Continuous Control
756. NeurIPS 2024Aligning Individual and Collective Objectives in Multi-Agent Cooperation
757. NeurIPS 2024Aligning Target-Aware Molecule Diffusion Models with Exact Energy Optimization
758. NeurIPS 2024Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms
759. NeurIPS 2024Alignment at Pre-training! Towards Native Alignment for Arabic LLMs
760. NeurIPS 2024AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers
761. NeurIPS 2024Amnesia as a Catalyst for Enhancing Black Box Pixel Attacks in Image Classification and Object Detection
762. NeurIPS 2024Amortized Active Causal Induction with Deep Reinforcement Learning
763. NeurIPS 2024Amortizing intractable inference in diffusion models for vision, language, and control
764. NeurIPS 2024An Analytical Study of Utility Functions in Multi-Objective Reinforcement Learning
765. NeurIPS 2024An Efficient High-dimensional Gradient Estimator for Stochastic Differential Equations
766. NeurIPS 2024An Offline Adaptation Framework for Constrained Multi-Objective Reinforcement Learning
767. NeurIPS 2024Artificial Generational Intelligence: Cultural Accumulation in Reinforcement Learning
768. NeurIPS 2024Assouad, Fano, and Le Cam with Interaction: A Unifying Lower Bound Framework and Characterization for Bandit Learnability
769. NeurIPS 2024AuctionNet: A Novel Benchmark for Decision-Making in Large-Scale Games
770. NeurIPS 2024Automated Multi-level Preference for MLLMs
771. NeurIPS 2024Autoregressive Policy Optimization for Constrained Allocation Tasks
772. NeurIPS 2024Axioms for AI Alignment from Human Feedback
773. NeurIPS 2024Balancing Context Length and Mixing Times for Reinforcement Learning at Scale
774. NeurIPS 2024Beating Adversarial Low-Rank MDPs with Unknown Transition and Bandit Feedback
775. NeurIPS 2024BECAUSE: Bilinear Causal Representation for Generalizable Offline Model-based Reinforcement Learning
776. NeurIPS 2024Belief-State Query Policies for User-Aligned POMDPs
777. NeurIPS 2024BenchMARL: Benchmarking Multi-Agent Reinforcement Learning
778. NeurIPS 2024Beyond Optimism: Exploration With Partially Observable Rewards
779. NeurIPS 2024Beyond Single Stationary Policies: Meta-Task Players as Naturally Superior Collaborators
780. NeurIPS 2024Bias and Volatility: A Statistical Framework for Evaluating Large Language Model's Stereotypes and the Associated Generation Inconsistency
781. NeurIPS 2024Bigger, Regularized, Optimistic: scaling for compute and sample efficient continuous control
782. NeurIPS 2024Bisimulation Metrics are Optimal Transport Distances, and Can be Computed Efficiently
783. NeurIPS 2024Boosting Sample Efficiency and Generalization in Multi-agent Reinforcement Learning via Equivariance
784. NeurIPS 2024Boosting Text-to-Video Generative Model with MLLMs Feedback
785. NeurIPS 2024BricksRL: A Platform for Democratizing Robotics and Reinforcement Learning Research and Education with LEGO
786. NeurIPS 2024Bridging Model-Based Optimization and Generative Modeling via Conservative Fine-Tuning of Diffusion Models
787. NeurIPS 2024C-GAIL: Stabilizing Generative Adversarial Imitation Learning with Control Theory
788. NeurIPS 2024CALE: Continuous Arcade Learning Environment
789. NeurIPS 2024Can large language models explore in-context?
790. NeurIPS 2024Can Learned Optimization Make Reinforcement Learning Less Difficult?
791. NeurIPS 2024Carrot and Stick: Eliciting Comparison Data and Beyond
792. NeurIPS 2024Catastrophic Goodhart: regularizing RLHF with KL divergence does not mitigate heavy-tailed reward misspecification
793. NeurIPS 2024CE-NAS: An End-to-End Carbon-Efficient Neural Architecture Search Framework
794. NeurIPS 2024CleanDiffuser: An Easy-to-use Modularized Library for Diffusion Models in Decision Making
795. NeurIPS 2024Coevolving with the Other You: Fine-Tuning LLM with Sequential Cooperative Multi-Agent Reinforcement Learning
796. NeurIPS 2024Compositional Automata Embeddings for Goal-Conditioned Reinforcement Learning
797. NeurIPS 2024Confident Natural Policy Gradient for Local Planning in $q_\pi$-realizable Constrained MDPs
798. NeurIPS 2024Constrained Latent Action Policies for Model-Based Offline Reinforcement Learning
799. NeurIPS 2024Contextual Bilevel Reinforcement Learning for Incentive Alignment
800. NeurIPS 2024Controlled maximal variability along with reliable performance in recurrent neural networks

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。