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 1,640 篇，第 19 / 33 页

901. NeurIPS 2025AegisGuard: RL-Guided Adapter Tuning for TEE-Based Efficient & Secure On-Device Inference
902. NeurIPS 2025Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization
903. NeurIPS 2025Agentic RL Scaling Law: Spontaneous Code Execution for Mathematical Problem Solving
904. NeurIPS 2025Align-DA: Align Score-based Atmospheric Data Assimilation with Multiple Preferences
905. NeurIPS 2025Aligning Transformers with Continuous Feedback via Energy Rank Alignment
906. NeurIPS 2025ALINE: Joint Amortization for Bayesian Inference and Active Data Acquisition
907. NeurIPS 2025AlphaZero Neural Scaling and Zipf's Law: a Tale of Board Games and Power Laws
908. NeurIPS 2025AMBER: Adaptive Mesh Generation by Iterative Mesh Resolution Prediction
909. NeurIPS 2025Analytic Energy-Guided Policy Optimization for Offline Reinforcement Learning
910. NeurIPS 2025Angles Don’t Lie: Unlocking Training‑Efficient RL Through the Model’s Own Signals
911. NeurIPS 2025Approximating Shapley Explanations in Reinforcement Learning
912. NeurIPS 2025AREAL: A Large-Scale Asynchronous Reinforcement Learning System for Language Reasoning
913. NeurIPS 2025ARIA: Training Language Agents with Intention-driven Reward Aggregation
914. NeurIPS 2025Ask a Strong LLM Judge when Your Reward Model is Uncertain
915. NeurIPS 2025Asymmetric REINFORCE for off-Policy Reinforcement Learning: Balancing positive and negative rewards
916. NeurIPS 2025AutoEdit: Automatic Hyperparameter Tuning for Image Editing
917. NeurIPS 2025Automaton Constrained Q-Learning
918. NeurIPS 2025Avoiding exp(R) scaling in RLHF through Preference-based Exploration
919. NeurIPS 2025Bayesian Ego-graph inference for Networked Multi-Agent Reinforcement Learning
920. NeurIPS 2025Behavior Injection: Preparing Language Models for Reinforcement Learning
921. NeurIPS 2025Benchmarking End-To-End Performance of AI-Based Chip Placement Algorithms
922. NeurIPS 2025Bernstein–von Mises for Adaptively Collected Data
923. NeurIPS 2025Better Estimation of the Kullback--Leibler Divergence Between Language Models
924. NeurIPS 2025Better NTK Conditioning: A Free Lunch from (ReLU) Nonlinear Activation in Wide Neural Networks
925. NeurIPS 2025Beyond Accuracy: Dissecting Mathematical Reasoning for LLMs Under Reinforcement Learning
926. NeurIPS 2025Beyond Average Value Function in Precision Medicine: Maximum Probability-Driven Reinforcement Learning for Survival Analysis
927. NeurIPS 2025Beyond Expectations: Quantile-Guided Alignment for Risk-Calibrated Language Models
928. NeurIPS 2025Beyond Least Squares: Uniform Approximation and the Hidden Cost of Misspecification
929. NeurIPS 2025Beyond Scalar Rewards: An Axiomatic Framework for Lexicographic MDPs
930. NeurIPS 2025Beyond the 80/20 Rule: High-Entropy Minority Tokens Drive Effective Reinforcement Learning for LLM Reasoning
931. NeurIPS 2025Beyond Verifiable Rewards: Scaling Reinforcement Learning in Language Models to Unverifiable Data
932. NeurIPS 2025Bi-Level Decision-Focused Causal Learning for Large-Scale Marketing Optimization: Bridging Observational and Experimental Data
933. NeurIPS 2025Bi-Level Knowledge Transfer for Multi-Task Multi-Agent Reinforcement Learning
934. NeurIPS 2025Bigger, Regularized, Categorical: High-Capacity Value Functions are Efficient Multi-Task Learners
935. NeurIPS 2025BioReason: Incentivizing Multimodal Biological Reasoning within a DNA-LLM Model
936. NeurIPS 2025Blending Complementary Memory Systems in Hybrid Quadratic-Linear Transformers
937. NeurIPS 2025Blindfolded Experts Generalize Better: Insights from Robotic Manipulation and Videogames
938. NeurIPS 2025Boosting Resilience of Large Language Models through Causality-Driven Robust Optimization
939. NeurIPS 2025Bootstrap Off-policy with World Model
940. NeurIPS 2025Boundary-to-Region Supervision for Offline Safe Reinforcement Learning
941. NeurIPS 2025BraVE: Offline Reinforcement Learning for Discrete Combinatorial Action Spaces
942. NeurIPS 2025BREAD: Branched Rollouts from Expert Anchors Bridge SFT & RL for Reasoning
943. NeurIPS 2025Breaking the Performance Ceiling in Reinforcement Learning requires Inference Strategies
944. NeurIPS 2025BridgeVLA: Input-Output Alignment for Efficient 3D Manipulation Learning with Vision-Language Models
945. NeurIPS 2025BTL-UI: Blink-Think-Link Reasoning Model for GUI Agent
946. NeurIPS 2025CAD-Coder: Text-to-CAD Generation with Chain-of-Thought and Geometric Reward
947. NeurIPS 2025Capturing Individual Human Preferences with Reward Features
948. NeurIPS 2025Causality Meets Locality: Provably Generalizable and Scalable Policy Learning for Networked Systems
949. NeurIPS 2025Centralized Reward Agent for Knowledge Sharing and Transfer in Multi-Task Reinforcement Learning
950. NeurIPS 2025Certifying Stability of Reinforcement Learning Policies using Generalized Lyapunov Functions

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。