推理模型论文趋势 2023–2026
链式推理、测试时计算与显式推理能力
统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 3,512 篇被归入该主题的论文。
主要结论
- 推理模型论文从 2023 年的 470 篇增长到 2026 年的 1,799 篇，三年间扩大到约 3.8 倍。
- NeurIPS 是发推理模型论文最多的会议，2023–2026 年共 1,253 篇，占四个会议总量的 36%。
- 交叉方向里涨得最快的是强化学习：同时属于两个主题的论文从 2023 年的 9 篇增至 2026 年的 437 篇。
- 在「前沿系统」的 4 个主题里，它的 2026 年论文数排第 3；同组增长最快的AI 智能体是 12 倍，推理模型是 3.8 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 271 | 57 | 109 | 33 | 470 |
| 2024 | 121 | 84 | 63 | 43 | 311 |
| 2025 | 500 | 203 | 159 | 70 | 932 |
| 2026 | 361 | 652 | 582 | 204 | 1,799 |
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 2026A Mechanistic Analysis of Looped Reasoning Language Models
- ICML 2026A Formal Comparison Between Chain of Thought and Latent Thought
- ICLR 2026A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models
- CVPR 2026Asking like Socrates Socrates helps VLMs understand remote sensing images
- NeurIPS 2025A Frustratingly Simple Yet Highly Effective Attack Baseline: Over 90% Success Rate Against the Strong Black-box Models of GPT-4.5/4o/o1
- ICML 2025A Reasoning-Based Approach to Cryptic Crossword Clue Solving
- ICLR 2025A Formal Framework for Understanding Length Generalization in Transformers
- CVPR 2025Argus: Vision-Centric Reasoning with Grounded Chain-of-Thought
- NeurIPS 2024Are Large Language Models Good Statisticians?
- ICML 2024Algorithm of Thoughts: Enhancing Exploration of Ideas in Large Language Models
- ICLR 2024Amortizing intractable inference in large language models
- CVPR 2024Generate Subgoal Images before Act: Unlocking the Chain-of-Thought Reasoning in Diffusion Model for Robot Manipulation with Multimodal Prompts
- NeurIPS 2023A benchmark of categorical encoders for binary classification
- ICML 2023Can We Scale Transformers to Predict Parameters of Diverse ImageNet Models?
- ICLR 2023Automatic Chain of Thought Prompting in Large Language Models
- CVPR 2023ActMAD: Activation Matching To Align Distributions for Test-Time-Training
- NeurIPS 2026A Solvable Model of Chain-of-Thought in In-Context Learning
- ICML 2026A Narrowing Geometry in Contaminated Reasoning
- ICLR 2026A State-Transition Framework for Efficient LLM Reasoning
- CVPR 2026Beyond Weak Supervision MLLMs-Guided Graded Knowledge Distillation for Unsupervised Camouflaged
全部推理模型论文
共 1,799 篇，第 7 / 36 页
- ICLR 2026CurES: From Gradient Analysis to Efficient Curriculum Learning for Reasoning LLMs
- ICLR 2026CyclicReflex: Improving Reasoning Models via Cyclical Reflection Token Scheduling
- ICLR 2026DAG-Math: Graph-Guided Mathematical Reasoning in LLMs
- ICLR 2026Deep Think with Confidence
- ICLR 2026DeepCompress: A Dual Reward Strategy for Dynamically Exploring and Compressing Reasoning Chains
- ICLR 2026DeepEyes: Incentivizing "Thinking with Images" via Reinforcement Learning
- ICLR 2026DeepSearch: Overcome the Bottleneck of Reinforcement Learning with Verifiable Rewards via Monte Carlo Tree Search
- ICLR 2026Demystifying and Enhancing the Efficiency of Large Language Model Based Search Agents
- ICLR 2026DePO: Demonstration-guided Policy Optimization for Molecular Optimization
- ICLR 2026DepthLM: Metric Depth from Vision Language Models
- ICLR 2026DESIGNER: Design-Logic-Guided Multidisciplinary Data Synthesis for LLM Reasoning
- ICLR 2026Diagnosing and Remedying Knowledge Deficiencies in LLMs via Label-free Curricular Meaningful Learning
- ICLR 2026DiffAdapt: Difficulty-Adaptive Reasoning for Token-Efficient LLM Inference
- ICLR 2026Differential Fine-Tuning Large Language Models Towards Better Diverse Reasoning Abilities
- ICLR 2026Difficulty–Diversity Collaborative Filtering for Data-Efficient LLM Fine-Tuning
- ICLR 2026Diffusion Language Models are Provably Optimal Parallel Samplers
- ICLR 2026Disrupting Hierarchical Reasoning: Adversarial Protection for Geographic Privacy in Multimodal Reasoning Models
- ICLR 2026Distilled Pretraining: A modern lens of Data, In-Context Learning and Test-Time Scaling
- ICLR 2026Distilling the Thought, Watermarking the Answer: A Principle Semantic Guided Watermark for Reasoning Large Language Models
- ICLR 2026Diversity-Enhanced Reasoning for Subjective Questions
- ICLR 2026Diversity-Incentivized Exploration for Versatile Reasoning
- ICLR 2026Do 3D Large Language Models Really Understand 3D Spatial Relationships?
- ICLR 2026Do Vision-Language Models Respect Contextual Integrity in Location Disclosure?
- ICLR 2026Don’t Pass@$k$: A Bayesian Framework for Large Language Model Evaluation
- ICLR 2026Doxing via the Lens: Revealing Location-related Privacy Leakage on Multi-modal Large Reasoning Models
- ICLR 2026DRAGON: Guard LLM Unlearning in Context via Negative Detection and Reasoning
- ICLR 2026Draw-In-Mind: Rebalancing Designer-Painter Roles in Unified Multimodal Models Benefits Image Editing
- ICLR 2026DRPO: Efficient Reasoning via Decoupled Reward Policy Optimization
- ICLR 2026DSSA: Dense-Sparse Switchable Attention for Seamless Short-to-Long Adaptation
- ICLR 2026Dyna-Mind: Learning to Simulate from Experience for Better AI Agents
- ICLR 2026DynaGuard: A Dynamic Guardian Model With User-Defined Policies
- ICLR 2026Dynamic Early Exit in Reasoning Models
- ICLR 2026Dynamics-Predictive Sampling for Active RL Finetuning of Large Reasoning Models
- ICLR 2026e3: Learning to Explore Enables Extrapolation of Test-Time Compute for LLMs
- ICLR 2026Early Signs of Steganographic Capabilities in Frontier LLMs
- ICLR 2026Easier Painting Than Thinking: Can Text-to-Image Models Set the Stage, but Not Direct the Play?
- ICLR 2026Echo: Towards Advanced Audio Comprehension via Audio-Interleaved Reasoning
- ICLR 2026Echoes as Anchors: Probabilistic Costs and Attention Refocusing in LLM Reasoning
- ICLR 2026EEPO: Exploration-Enhanced Policy Optimization via Sample-Then-Forget
- ICLR 2026Efficient Ensemble Conditional Independence Test Framework for Causal Discovery
- ICLR 2026Efficient Multimodal Spatial Reasoning via Dynamic and Asymmetric Routing
- ICLR 2026Efficient Reasoning with Balanced Thinking
- ICLR 2026Efficient Test-Time Scaling for Small Vision-Language Models
- ICLR 2026Efficient Turing Machine Simulation with Transformers
- ICLR 2026Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
- ICLR 2026Emergence of Superposition: Unveiling the Training Dynamics of Chain of Continuous Thought
- ICLR 2026Emergent Discrete Controller Modules for Symbolic Planning in Transformers
- ICLR 2026Emergent Hierarchical Reasoning in LLMs through Reinforcement Learning
- ICLR 2026EmotionThinker: Prosody-Aware Reinforcement Learning for Explainable Speech Emotion Reasoning
- ICLR 2026Energy-Based Transformers are Scalable Learners and Thinkers
在 Claude、Cursor 里直接问这个趋势
接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。
可以直接复制这句话问 AI
用 paperlist 查推理模型在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？
AI 会调用的工具：get_topic_stats {"topic": "reasoning-models"}
常见问题
- 2023–2026 年四大会议一共有多少篇推理模型论文？
- 共 3,512 篇，按年份分别是 2023 年 470 篇、2024 年 311 篇、2025 年 932 篇、2026 年 1,799 篇。
- NeurIPS 2026 有多少篇推理模型论文？
- NeurIPS 2026 有 361 篇推理模型论文，上一届是 500 篇。
- ICLR 2026 有多少篇推理模型论文？
- ICLR 2026 有 652 篇推理模型论文，上一届是 203 篇。
- ICML 2026 有多少篇推理模型论文？
- ICML 2026 有 582 篇推理模型论文，上一届是 159 篇。
- CVPR 2026 有多少篇推理模型论文？
- CVPR 2026 有 204 篇推理模型论文，上一届是 70 篇。
- 哪个会议的推理模型论文最多？
- NeurIPS，2023–2026 年共 1,253 篇。