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 2,494 篇，第 13 / 50 页

601. NeurIPS 2026SIRAS: Sibling-Relative Advantage Shaping for Reinforcement Learning from Verifiable Rewards
602. NeurIPS 2026Skill-Coupled Policy Optimization with Calibrated Group-Wise Advantage Estimation
603. NeurIPS 2026Skill-SD: Skill-Conditioned Self-Distillation for Multi-turn LLM Agents
604. NeurIPS 2026SkillForge: Co-Evolving Skills and Agents via Dynamic Skill Lifecycles
605. NeurIPS 2026SLOPE: Optimistic Potential Landscape Shaping for Model-based Reinforcement Learning
606. NeurIPS 2026Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots
607. NeurIPS 2026SOC-ICNN: From Polyhedral to Conic Geometry for Learning Convex Surrogate Functions
608. NeurIPS 2026Soft Forward-Backward Representations for Zero-shot Reinforcement Learning with General Utilities
609. NeurIPS 2026SOLE-R1: Video-Language Reasoning as the Sole Reward for On-Robot Reinforcement Learning
610. NeurIPS 2026Spatial-IQ: Deconstructing Spatial Intelligence via Hierarchical Capability Tests
611. NeurIPS 2026SpatialFlow-GRPO: Where Spatial Credit Drives Image Editing
612. NeurIPS 2026SPECS: Faster Test-Time Scaling through Speculative Drafts and Dynamic Switching
613. NeurIPS 2026Spectral Geometry of Attention: From Information Routing to Uncertainty
614. NeurIPS 2026Spectral Representations for Provably Robust Offline Meta-Reinforcement Learning from Bagged Rewards
615. NeurIPS 2026Spiking neural network initialization for scale-invariant maximization of entropy
616. NeurIPS 2026Split the Differences, Pool the Rest: Provably Efficient Multi-Objective Imitation
617. NeurIPS 2026Split-RL: Local Conflict Resolution in Reinforcement Learning
618. NeurIPS 2026SPRING: Solver-guided Process Rewards for Novel Logical Reasoning Steps Generation
619. NeurIPS 2026SR-GRPO: Stable Rank as an Intrinsic Geometric Reward for Large Language Model Alignment
620. NeurIPS 2026SRL-MPC: Shape-Aware Reinforcement Learned Model Predictive Control
621. NeurIPS 2026Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
622. NeurIPS 2026Stabilizing Policy Optimization via Logits Convexity
623. NeurIPS 2026Stable and Granular Policy Optimization for Generative Recommendation
624. NeurIPS 2026StainNFT: Curriculum-Gated Multi-Reward Post-Training for Pathology-Faithful Virtual Staining
625. NeurIPS 2026STAPO: Stabilizing Reinforcement Learning for LLMs by Silencing Rare Spurious Tokens
626. NeurIPS 2026STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability
627. NeurIPS 2026StateTree: Enhancing Long-term Dialogue Reasoning via Reinforcement Learning
628. NeurIPS 2026Statistical Complexity of Soft Bellman Residual Minimization
629. NeurIPS 2026Steer2Edit: From Activation Steering to Component-Level Editing
630. NeurIPS 2026Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces
631. NeurIPS 2026Step-wise Rubric Rewards for LLM Reasoning
632. NeurIPS 2026Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
633. NeurIPS 2026StraTA: Incentivizing Agentic Reinforcement Learning with Strategic Trajectory Abstraction
634. NeurIPS 2026Strategic Decision Focused Learning
635. NeurIPS 2026Strengthening LLMs for Tabular Prediction with Structural Priors
636. NeurIPS 2026STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning
637. NeurIPS 2026Structural Entropy Optimized Communication for Multi-Agent Reinforcement Learning
638. NeurIPS 2026Structure-aware Reinforcement Learning for Protein Directed Evolution
639. NeurIPS 2026Subprocess-Constrained Markov Decision Processes
640. NeurIPS 2026Survive or Collapse: The Asymmetric Roles of Data Gating and Reward Grounding in Self-Play RL
641. NeurIPS 2026SWE-Protégé: Learning to Selectively Collaborate With an Expert Unlocks Small Language Models as Software Engineering Agents
642. NeurIPS 2026Synsema: Syntax-Guided Learning of Semantically Valid Programs
643. NeurIPS 2026Tail-Risk-Aware Stackelberg Learning
644. NeurIPS 2026Taming CoT Obfuscation in VLMs: From Mechanistic Evidence to Activation-Level Enforcement
645. NeurIPS 2026Taming the Curses of Multiagency in Robust Markov Games with Large State Space through Linear Function Approximation
646. NeurIPS 2026TANGO: RNA Topology and Geometry Co-Design
647. NeurIPS 2026TARP: Trace-Anchored Regularization Prior for Retaining Stepwise Reasoning
648. NeurIPS 2026Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher
649. NeurIPS 2026TEMPO: Temporal Enforcement via Mode-Separated Policy Optimization for Trustworthy LLM Backtesting
650. NeurIPS 2026Temporal Consistency Improves Generalization in Contextual Offline Meta 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。