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 1,021 篇，第 15 / 21 页

701. ICML 2026Regulating Anatomy-Aware Rewards via Trajectory-Integral Feedback for Volumetric Computed Tomography Analysis
702. ICML 2026Reinforced Sequential Monte Carlo for Amortised Sampling
703. ICML 2026Reinforcement Learning for Reachability: Guaranteeing Asymptotic Optimality
704. ICML 2026Reinforcement Learning for Tool-Calling Agents in Fast Healthcare Interoperability Resources (FHIR)
705. ICML 2026Reinforcement Learning via Self-Distillation
706. ICML 2026Reinforcement Learning with Action-Triggered Observations
707. ICML 2026Reinforcement Learning with Discrete Diffusion Policies for Combinatorial Action Spaces
708. ICML 2026Reinforcement Learning with Pairwise Preferences in Long-Term Decision Problems
709. ICML 2026Reinforcement Learning with Verifiable Rewards: GRPO's Loss, Dynamics, and Success Amplification
710. ICML 2026Reinforcement-aware Knowledge Distillation for LLM Reasoning
711. ICML 2026Reinforcing Real-world Service Agents: Balancing Utility and Cost in Task-oriented Dialogue
712. ICML 2026ReJump: A Tree-Jump Representation for Analyzing and Improving LLM Reasoning
713. ICML 2026ReLAM: Learning Anticipation Model for Rewarding Visual Robotic Manipulation
714. ICML 2026Reliability-Aware LLM Alignment from Inconsistent Human Feedback
715. ICML 2026RELO: Reinforcement Learning to Localize for Visual Object Tracking
716. ICML 2026Removing Sandbagging in LLMs by Training with Weak Supervision
717. ICML 2026Reparameterization Flow Policy Optimization
718. ICML 2026Reparameterization Proximal Policy Optimization
719. ICML 2026rePIRL: Learn PRM with Inverse RL for LLM Reasoning
720. ICML 2026Replay Failures as Successes: Sample-Efficient Reinforcement Learning for Instruction Following
721. ICML 2026RePro: Training Language Models to Faithfully Recycle the Web for Pretraining
722. ICML 2026ReSeek: A Self-Correcting Framework for Search Agents with Instructive Rewards
723. ICML 2026Resource-Efficient Reinforcement for Reasoning Large Language Models via Dynamic One-Shot Policy Refinement
724. ICML 2026ResRL: Boosting LLM Reasoning via Negative Sample Projection Residual Reinforcement Learning
725. ICML 2026ReTabSyn: Realistic Tabular Data Synthesis via Reinforcement Learning
726. ICML 2026Retaining by Doing: The Role of On-Policy Data in Mitigating Forgetting
727. ICML 2026Rethinking Human Intent-to-CAD: Parametric CAD Model Generation via Cooperative Multi-Task Alignment and Spatial-Aware Reinforcement Learning
728. ICML 2026Rethinking Neural Network Learning Rates: A Stackelberg Perspective
729. ICML 2026Rethinking the Design Space of Reinforcement Learning for Diffusion Models: On the Importance of Likelihood Estimation Beyond Loss Design
730. ICML 2026Rethinking the Hardness of PbRL: A Provable General Regret Bound
731. ICML 2026Rethinking the Reranker: Boundary-Aware Evidence Selection for Robust Retrieval-Augmented Generation
732. ICML 2026Rethinking the Trust Region in LLM Reinforcement Learning
733. ICML 2026Rethinking Thinking Tokens: LLMs as Improvement Operators
734. ICML 2026Retro-Expert: Collaborative Reasoning for Interpretable Retrosynthesis
735. ICML 2026RetrOrchestrator: A Multi-Step Retrosynthesis Agent Dynamically Orchestrating Single-Step Transition Models
736. ICML 2026Return-Critic: Bridging Goal Discrepancy for Efficient Visual Reinforcement Learning
737. ICML 2026Return-to-Go Is More Than a Number: Q-Guided Alignment for Return-Conditioned Supervised Learning
738. ICML 2026Reuse your FLOPs: Scaling RL on Hard Problems by Conditioning on Very Off-Policy Prefixes
739. ICML 2026Reusing Trajectories in Policy Gradients Enables Fast Convergence
740. ICML 2026Revealing Behavioral Plasticity in Large Language Models: A Token-Conditional Perspective
741. ICML 2026Reverse Flow Matching: A Unified Framework for Online Reinforcement Learning with Diffusion and Flow Policies
742. ICML 2026Revisiting Distribution Correction Estimation for Offline Imitation Learning with Suboptimal Dataset
743. ICML 2026Revisiting OOD Generalization in Programmatic RL
744. ICML 2026Revisiting Regularized Policy Optimization for Stable and Efficient Reinforcement Learning in Two-Player Games
745. ICML 2026Revisiting Zeroth-Order Hessian Approximation: A Single-Step Policy Optimization Lens
746. ICML 2026Reward and Guidance through Rubrics: Promoting Exploration to Improve Multi-Domain Reasoning
747. ICML 2026Reward Hacking Benchmark: Measuring Exploits in LLM Agents with Tool Use
748. ICML 2026Reward Learning through Ranking Mean Squared Error
749. ICML 2026Reward Modeling from Natural Language Human Feedback
750. ICML 2026Reward Redistribution for CVaR MDPs using a Bellman Operator on L-infinity

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。