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 19 / 21 页

901. ICML 2026The Two-Hump Problem: Bridging the Difficulty Gap in Mathematical Reinforcement Learning
902. ICML 2026The Unlearnability Phenomenon in RLVR for Language Models
903. ICML 2026The Value Function Semi-Algebraic Set in Partially Observable Markov Decision Processes
904. ICML 2026Theoretical Perspectives on Data Quality and Synergistic Effects in Pre- and Post-Training Reasoning Models
905. ICML 2026ThetaEvolve: Test-time Learning on Open Problems
906. ICML 2026Think Fast and Slow: Step-Level Cognitive Depth Adaptation for LLM Agents
907. ICML 2026Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models
908. ICML 2026Thinking in Latent Space: Progressive Multimodal Simplification for Visual Reasoning
909. ICML 2026This State Looks Like That: Self-Interpretable Reinforcement Learning Agents using Prototype Soft Actor-Critic
910. ICML 2026ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning
911. ICML 2026ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models
912. ICML 2026Threshold-Guided Optimization for Visual Generative Models
913. ICML 2026ThunderAgent: A Fast, Simple, and Program-Aware Agentic Inference System
914. ICML 2026TIC-VLA: A Think-in-Control Vision-Language-Action Model for Robot Navigation in Dynamic Environments
915. ICML 2026Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning
916. ICML 2026Time-Consistent Robust Multi-Objective Reinforcement Learning via a Bellman–Isaacs Weight-Adversary Recursion
917. ICML 2026TimeRewarder: Learning Dense Reward from Passive Videos via Frame-wise Temporal Distance
918. ICML 2026TMS: Trajectory-Mixed Supervision for On-Policy Self Distillation
919. ICML 2026TodoEvolve: Learning to Architect Agent Planning Systems
920. ICML 2026Token-Sparse Medical Multimodal Reasoning via Dual-Stream Reinforcement Learning
921. ICML 2026ToolOrchestra: Elevating Intelligence via Efficient Model and Tool Orchestration
922. ICML 2026Tournament Style RL: Stabilizing Policy Optimization on Non Verifiable Problems
923. ICML 2026Toward Subspace-Perturbed Trajectory-Aware Backdoor Attacks in Deep Reinforcement Learning
924. ICML 2026Toward Training Superintelligent Software Agents through Self-Play SWE-RL
925. ICML 2026Towards Achieving Optimal Strong Regret and Constraint Violation via Computationally Efficient Model-free RL
926. ICML 2026Towards Cold-Start Drafting and Continual Refining: A Value-Driven Memory Approach with Application to NPU Kernel Synthesis
927. ICML 2026Towards Complete Multi-Agent Coordination Policy Learning via Denoising Maximum Entropy Optimization
928. ICML 2026Towards Efficient and Expressive Offline RL via Flow-Anchored Noise-conditioned Q-Learning
929. ICML 2026Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression
930. ICML 2026Towards Execution-Grounded Automated AI Research
931. ICML 2026Towards High-Fidelity CAD Generation via LLM-Driven Program Generation and Text-Based B-Rep Primitive Grounding
932. ICML 2026Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training
933. ICML 2026Towards Parameter-Free Temporal Difference Learning
934. ICML 2026Towards Pareto-Optimal Tool-Integrated Agents with Pareto Ranking Policy Optimization
935. ICML 2026Towards Practical World Model-based Reinforcement Learning for Vision-Language-Action Models
936. ICML 2026TQL: Scaling Q-Functions with Transformers by Preventing Attention Collapse
937. ICML 2026TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evaluation
938. ICML 2026TraCeS: Learning Per-Timestep Constraint-Violation Credit from Sparse Trajectory-Level Labels
939. ICML 2026Tracking Drift: Variation-Aware Entropy Scheduling for Non-Stationary Reinforcement Learning
940. ICML 2026Train for Truth, Keep the Skills: Binary Retrieval-Augmented Reward Mitigates Hallucinations
941. ICML 2026Training AI Co-Scientists Using Rubric Rewards
942. ICML 2026Training Diffusion Language Models for Black-Box Optimization
943. ICML 2026Trajectory-Level Data Augmentation for Offline Reinforcement Learning
944. ICML 2026Transferable Reinforcement Learning via Probabilistic Latent Embeddings and Dynamic Policy Adaptation for Sim-to-Real Deployment
945. ICML 2026Transformers with RL or SFT Provably Learn Sparse Boolean Functions, But Differently
946. ICML 2026Transitivity Meets Cyclicity: Explicit Preference Decomposition for Dynamic Large Language Model Alignment
947. ICML 2026Transport or Discard: Robust Unbalanced Optimal Transport for Cross-Domain Policy Adaptation
948. ICML 2026TreePO: Enhancing Policy Efficacy and Inference Efficiency with Tree Modeling
949. ICML 2026Triadic Dynamics Aware Diffusion Posterior Sampling for Inverse Problems: Optimizing Guidance and Stochasticity Schedules
950. ICML 2026TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios

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。