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 911 篇，第 15 / 19 页

701. ICLR 2026Scaling Linear Attention with Sparse State Expansion
702. ICLR 2026Scaling Synthetic Task Generation for Agents via Exploration
703. ICLR 2026Scheduling Your LLM Reinforcement Learning with Reasoning Trees
704. ICLR 2026SCOPED: Score–Curvature Out-of-distribution Proximity Evaluator for Diffusion
705. ICLR 2026SCRIBES: Web-Scale Script-Based Semi-Structured Data Extraction with Reinforcement Learning
706. ICLR 2026Sculptor: Empowering LLMs with Cognitive Agency via Active Context Management
707. ICLR 2026Search Self-Play: Pushing the Frontier of Agent Capability without Supervision
708. ICLR 2026Seeing, Listening, Remembering, and Reasoning: A Multimodal Agent with Long-Term Memory
709. ICLR 2026Selective Expert Guidance for Effective and Diverse Exploration in Reinforcement Learning of LLMs
710. ICLR 2026Self-Aligned Reward: Towards Effective and Efficient Reasoners
711. ICLR 2026Self-Evolving Vision-Language Models for Image Quality Assessment via Voting and Ranking
712. ICLR 2026SELF-HARMONY: LEARNING TO HARMONIZE SELF-SUPERVISION AND SELF-PLAY IN TEST-TIME REINFORCEMENT LEARNING
713. ICLR 2026Self-Improving Skill Learning for Robust Skill-based Meta-Reinforcement Learning
714. ICLR 2026Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
715. ICLR 2026Self-Rewarding Vision-Language Model via Reasoning Decomposition and Multi-Reward Policy Optimization
716. ICLR 2026SEMA: Simple yet Effective Learning for Multi-Turn Jailbreak Attacks
717. ICLR 2026Semantic-aware Wasserstein Policy Regularization for Large Language Model Alignment
718. ICLR 2026SHAPO: Sharpness-Aware Policy Optimization for Safe Exploration
719. ICLR 2026Shift-Tolerant Allocation via Black-Litterman Using Conditional Diffusion Estimates
720. ICLR 2026Shop-R1: Rewarding LLMs to Simulate Human Behavior in Online Shopping via Reinforcement Learning
721. ICLR 2026Shortcut Diffusion Training with Cumulative Consistency Loss: An Optimal Control View
722. ICLR 2026Shuffle-R1: Efficient RL framework for Multimodal Large Language Models via Data-centric Dynamic Shuffle
723. ICLR 2026SimpleTIR: End-to-End Reinforcement Learning for Multi-Turn Tool-Integrated Reasoning
724. ICLR 2026SimpleVLA-RL: Scaling VLA Training via Reinforcement Learning
725. ICLR 2026Simplicial Embeddings Improve Sample Efficiency in Actor–Critic Agents
726. ICLR 2026Single-stream Policy Optimization
727. ICLR 2026SK2Decompile: LLM-based Two-Phase Binary Decompilation from Skeleton to Skin
728. ICLR 2026SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models
729. ICLR 2026Skill Learning via Policy Diversity Yields Identifiable Representations for Reinforcement Learning
730. ICLR 2026SkillFactory: Self-Distillation for Learning Cognitive Behaviors
731. ICLR 2026Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning
732. ICLR 2026SmartChunk Retrieval: Query-Aware Chunk Compression with Planning for Efficient Document RAG
733. ICLR 2026Smarter Not Harder: Generative Process Evaluation with Intrinsic-Signal Driving and Ability‑Adaptive Reward Shaping
734. ICLR 2026SocialJax: An Evaluation Suite for Multi-agent Reinforcement Learning in Sequential Social Dilemmas
735. ICLR 2026Soft Tokens, Hard Truths
736. ICLR 2026Solving Football by Exploiting Equilibrium Structure of 2p0s Differential Games with One-Sided Information
737. ICLR 2026Solving General-Utility Markov Decision Processes in the Single-Trial Regime with Online Planning
738. ICLR 2026Solving Parameter-Robust Avoid Problems with Unknown Feasibility using Reinforcement Learning
739. ICLR 2026SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
740. ICLR 2026SPACeR: Self-Play Anchoring with Centralized Reference Models
741. ICLR 2026Sparse but Critical: A Token-Level Analysis of Distributional Shifts in RLVR Fine-Tuning of LLMs
742. ICLR 2026SpatialLadder: Progressive Training for Spatial Reasoning in Vision-Language Models
743. ICLR 2026SPECS: Decoupling Multimodal Learning via Self-distilled Preference-based Cold Start
744. ICLR 2026Spectral Bellman Method: Unifying Representation and Exploration in RL
745. ICLR 2026SpeechJudge: Towards Human-Level Judgment for Speech Naturalness
746. ICLR 2026SPELL: Self-Play Reinforcement Learning for Evolving Long-Context Language Models
747. ICLR 2026SPG: Sandwiched Policy Gradient for Masked Diffusion Language Models
748. ICLR 2026SPIRAL: Self-Play on Zero-Sum Games Incentivizes Reasoning via Multi-Agent Multi-Turn Reinforcement Learning
749. ICLR 2026SportR: A Benchmark for Multimodal Large Language Model Reasoning in Sports
750. ICLR 2026Spotlight on Token Perception for Multimodal Reinforcement Learning

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。