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 2,079 篇，第 16 / 42 页

751. ICML 2026Reward Shaping Control Variates for Off-Policy Evaluation Under Sparse Rewards
752. ICML 2026Reward-Preserving Counterfactual State Editing for Offline Reinforcement Learning
753. ICML 2026RiskZero: Plan More to Risk Less with a Learned Model
754. ICML 2026RL with Learnable Textual Feedback: A Bilevel Approach
755. ICML 2026RL-SPH: Learning to Achieve Feasible Solutions for Integer Linear Programs
756. ICML 2026RL4RLA: Teaching ML to Discover Randomized Linear Algebra Algorithms Through Curriculum Design and Graph-Based Search
757. ICML 2026RLAnything: Forge Environment, Policy, and Reward Model in Completely Dynamic RL System
758. ICML 2026RLCracker: Evaluating the Worst-Case Vulnerability of LLM Watermarks with Adaptive RL Attacks
759. ICML 2026RLVE: Scaling Up Reinforcement Learning for Language Models with Adaptive Verifiable Environments
760. ICML 2026RN-D: Discretized Categorical Actors for On-Policy Reinforcement Learning
761. ICML 2026Robust Contextual Optimization with Missing Covariates
762. ICML 2026Robust In-Context Reinforcement Learning Under Reward Poisoning Attacks
763. ICML 2026Robust Sequential Experimental Design for A/B Testing
764. ICML 2026Robust-U1: Can MLLMs Self-Recover Corrupted Visual Content for Robust Understanding?
765. ICML 2026Role-Level Inductive Bias for Cross-Task Generalization in Multi-Agent Reinforcement Learning
766. ICML 2026RSAgent: Learning to Reason and Act via Multi-Turn Tool Invocations for Text-Guided Segmentation
767. ICML 2026Rubric Curriculum RL: Exploiting the Generation-Verification Gap in Non-Verifiable Domains
768. ICML 2026RuCL: Stratified Rubric-Based Curriculum Learning for Multimodal Large Language Model Reasoning
769. ICML 2026RulePlanner: All-in-One Reinforcement Learner for Unifying Design Rules in 3D Floorplanning
770. ICML 2026Safe In-Context Reinforcement Learning
771. ICML 2026Safe Reinforcement Learning with Preference-based Constraint Inference
772. ICML 2026Safety Alignment of LMs via Non-cooperative Games
773. ICML 2026Safety Game: Inference-Time Alignment of Black-Box LLMs via Constrained Optimization
774. ICML 2026Safety Generalization Under Distribution Shift in Safe Reinforcement Learning: A Diabetes Testbed
775. ICML 2026Safety Recovery in Reasoning Models Is Only a Few Early Steering Steps Away
776. ICML 2026SAGE: Shaping Anchors for Guided Exploration in RLVR of LLMs
777. ICML 2026Salus: Strategic Diagnostic Testing for Complex Diagnosis via Multi-Agent Reinforcement Learning
778. ICML 2026Sample-Efficient Diffusion-based Reinforcement Learning with Critic Guidance
779. ICML 2026SARL: Structure-Aligned Reinforcement Learning for Bridging the Perception-Action Gap in Airspace
780. ICML 2026Scalable and General Whole-Body Control for Cross-Humanoid Locomotion
781. ICML 2026Scalable Option Learning in High-Throughput Environments
782. ICML 2026Scalable Power Sampling: Unlocking Efficient, Training-Free Reasoning for LLMs via Distribution Sharpening
783. ICML 2026Scalable Reinforcement Learning via Adaptive Batch Scaling
784. ICML 2026Scalable Traffic Signal Control with Shared Policy Framework
785. ICML 2026ScaleMoE: Mixture-of-Experts for Scalable Continuous Control in Actor-Critic Reinforcement Learning
786. ICML 2026Scaling Agentic Verifier for Competitive Coding
787. ICML 2026Scaling Generative Verifiers For Natural Language Mathematical Proof Verification And Selection
788. ICML 2026Scaling Long-Horizon Agent via Context Folding
789. ICML 2026Scaling Multi-Agent Environment Co-Design with Diffusion Models
790. ICML 2026Scaling the Scaling Logic: Agentic Meta-Synthesis of Logic Reasoning
791. ICML 2026Scaling up Multi-Turn Off-Policy RL and Multi-Agent Tree Search for LLM Step-Provers
792. ICML 2026Scaling, Benchmarking, and Reasoning of Vision-Language Agents for Mobile GUI Navigation
793. ICML 2026ScenePilot: Controllable Boundary-Driven Critical Scenario Generation for Autonomous Driving
794. ICML 2026Scheduling Thoughts: Learning the Order of Thought in Diffusion Language Models
795. ICML 2026SCOPE: Selective Conformal Optimized Pairwise LLM Judging
796. ICML 2026Search-R2: Enhancing Search-Integrated Reasoning via Actor-Refiner Collaboration
797. ICML 2026Second-Order Smooth Planning with Optimal-Transport Bellman Smoothing
798. ICML 2026Secure Multi-agent Reinforcement Learning for Service Systems with Affinity and Byzantine Nodes: Stability Analysis and Protection Design
799. ICML 2026See First, Reason Later: Mutual Information-Guided Reinforcement Learning for Vision-Language Models
800. ICML 2026See, Act, Adapt: Active Perception for Unsupervised Cross-Domain Visual Adaptation via Personalized VLM-Guided Agent

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。