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 79 / 138 页

3901. NeurIPS 2025AutoEdit: Automatic Hyperparameter Tuning for Image Editing
3902. NeurIPS 2025Automaton Constrained Q-Learning
3903. NeurIPS 2025Avoiding exp(R) scaling in RLHF through Preference-based Exploration
3904. NeurIPS 2025Bayesian Ego-graph inference for Networked Multi-Agent Reinforcement Learning
3905. NeurIPS 2025Behavior Injection: Preparing Language Models for Reinforcement Learning
3906. NeurIPS 2025Benchmarking End-To-End Performance of AI-Based Chip Placement Algorithms
3907. NeurIPS 2025Bernstein–von Mises for Adaptively Collected Data
3908. NeurIPS 2025Better Estimation of the Kullback--Leibler Divergence Between Language Models
3909. NeurIPS 2025Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks
3910. NeurIPS 2025Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning
3911. NeurIPS 2025Beyond Average Value Function in Precision Medicine: Maximum Probability-Driven Reinforcement Learning for Survival Analysis
3912. NeurIPS 2025Beyond Expectations: Quantile-Guided Alignment for Risk-Calibrated Language Models
3913. NeurIPS 2025Beyond Least Squares: Uniform Approximation and the Hidden Cost of Misspecification
3914. NeurIPS 2025Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs
3915. NeurIPS 2025Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
3916. NeurIPS 2025Beyond Verifiable Rewards: Scaling Reinforcement Learning in Language Models to Unverifiable Data
3917. NeurIPS 2025Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data
3918. NeurIPS 2025Bi-Level Knowledge Transfer for Multi-Task Multi-Agent Reinforcement Learning
3919. NeurIPS 2025Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
3920. NeurIPS 2025BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model
3921. NeurIPS 2025Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers
3922. NeurIPS 2025Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames
3923. NeurIPS 2025Boosting Resilience of Large Language Models through Causality-Driven Robust Optimization
3924. NeurIPS 2025Bootstrap Off-policy with World Model
3925. NeurIPS 2025Boundary-to-Region Supervision for Offline Safe Reinforcement Learning
3926. NeurIPS 2025BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces
3927. NeurIPS 2025BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning
3928. NeurIPS 2025Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies
3929. NeurIPS 2025BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
3930. NeurIPS 2025BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent
3931. NeurIPS 2025CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward
3932. NeurIPS 2025Capturing Individual Human Preferences with Reward Features
3933. NeurIPS 2025Causality Meets Locality: Provably Generalizable and Scalable Policy Learning for Networked Systems
3934. NeurIPS 2025Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning
3935. NeurIPS 2025Certifying Stability of Reinforcement Learning Policies using Generalized Lyapunov Functions
3936. NeurIPS 2025ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding
3937. NeurIPS 2025Checklists Are Better Than Reward Models For Aligning Language Models
3938. NeurIPS 2025CHPO: Constrained Hybrid-action Policy Optimization for Reinforcement Learning
3939. NeurIPS 2025Classical Planning with LLM-Generated Heuristics: Challenging the State of the Art with Python Code
3940. NeurIPS 2025CLAWS:Creativity detection for LLM-generated solutions using Attention Window of Sections
3941. NeurIPS 2025Co-Reinforcement Learning for Unified Multimodal Understanding and Generation
3942. NeurIPS 2025Coarse-to-fine Q-Network with Action Sequence for Data-Efficient Reinforcement Learning
3943. NeurIPS 2025COGNAC: Cooperative Graph-based Networked Agent Challenges for Multi-Agent Reinforcement Learning
3944. NeurIPS 2025Cognitive Predictive Processing: A Human-inspired Framework for Adaptive Exploration in Open-World Reinforcement Learning
3945. NeurIPS 2025COLA: Towards Efficient Multi-Objective Reinforcement Learning with Conflict Objective Regularization in Latent Space
3946. NeurIPS 2025Compiler-R1: Towards Agentic Compiler Auto-tuning with Reinforcement Learning
3947. NeurIPS 2025Complexity Scaling Laws for Neural Models using Combinatorial Optimization
3948. NeurIPS 2025Composing Linear Layers from Irreducibles
3949. NeurIPS 2025Composite Flow Matching for Reinforcement Learning with Shifted-Dynamics Data
3950. NeurIPS 2025Compositional Monte Carlo Tree Diffusion for Extendable Planning

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。