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 1,253 篇，第 13 / 26 页
- NeurIPS 2025Matryoshka Pilot: Learning to Drive Black-Box LLMs with LLMs
- NeurIPS 2025Measuring the Faithfulness of Thinking Drafts in Large Reasoning Models
- NeurIPS 2025Mellow: a small audio language model for reasoning
- NeurIPS 2025MesaTask: Towards Task-Driven Tabletop Scene Generation via 3D Spatial Reasoning
- NeurIPS 2025MiCo: Multi-image Contrast for Reinforcement Visual Reasoning
- NeurIPS 2025Mind the Gap: Bridging Thought Leap for Improved Chain-of-Thought Tuning
- NeurIPS 2025MindOmni: Unleashing Reasoning Generation in Vision Language Models with RGPO
- NeurIPS 2025miniF2F-Lean Revisited: Reviewing Limitations and Charting a Path Forward
- NeurIPS 2025MINT-CoT: Enabling Interleaved Visual Tokens in Mathematical Chain-of-Thought Reasoning
- NeurIPS 2025MIR-Bench: Can Your LLM Recognize Complicated Patterns via Many-Shot In-Context Reasoning?
- NeurIPS 2025MIRAGE: A Benchmark for Multimodal Information-Seeking and Reasoning in Agricultural Expert-Guided Conversations
- NeurIPS 2025Mitigating Overthinking in Large Reasoning Models via Manifold Steering
- NeurIPS 2025Mixing Expert Knowledge: Bring Human Thoughts Back To the Game of Go
- NeurIPS 2025MLLM-For3D: Adapting Multimodal Large Language Model for 3D Reasoning Segmentation
- NeurIPS 2025MMaDA: Multimodal Large Diffusion Language Models
- NeurIPS 2025MMAR: A Challenging Benchmark for Deep Reasoning in Speech, Audio, Music, and Their Mix
- NeurIPS 2025MMPerspective: Do MLLMs Understand Perspective? A Comprehensive Benchmark for Perspective Perception, Reasoning, and Robustness
- NeurIPS 2025MMTU: A Massive Multi-Task Table Understanding and Reasoning Benchmark
- NeurIPS 2025Monitoring Risks in Test-Time Adaptation
- NeurIPS 2025More Thinking, Less Seeing? Assessing Amplified Hallucination in Multimodal Reasoning Models
- NeurIPS 2025MRO: Enhancing Reasoning in Diffusion Language Models via Multi-Reward Optimization
- NeurIPS 2025Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
- NeurIPS 2025Multi-head Transformers Provably Learn Symbolic Multi-step Reasoning via Gradient Descent
- NeurIPS 2025Multimodal Causal Reasoning for UAV Object Detection
- NeurIPS 2025Multimodal Tabular Reasoning with Privileged Structured Information
- NeurIPS 2025Multipole Attention for Efficient Long Context Reasoning
- NeurIPS 2025Multiverse: Your Language Models Secretly Decide How to Parallelize and Merge Generation
- NeurIPS 2025MuSLR: Multimodal Symbolic Logical Reasoning
- NeurIPS 2025NaturalReasoning: Reasoning in the Wild with 2.8M Challenging Questions
- NeurIPS 2025NeSyPr: Neurosymbolic Proceduralization For Efficient Embodied Reasoning
- NeurIPS 2025Neurosymbolic Diffusion Models
- NeurIPS 2025Noise Hypernetworks: Amortizing Test-Time Compute in Diffusion Models
- NeurIPS 2025NoisyGRPO: Incentivizing Multimodal CoT Reasoning via Noise Injection and Bayesian Estimation
- NeurIPS 2025NoisyRollout: Reinforcing Visual Reasoning with Data Augmentation
- NeurIPS 2025nvBench 2.0: Resolving Ambiguity in Text-to-Visualization through Stepwise Reasoning
- NeurIPS 2025OCRBench v2: An Improved Benchmark for Evaluating Large Multimodal Models on Visual Text Localization and Reasoning
- NeurIPS 2025OMEGA: Can LLMs Reason Outside the Box in Math? Evaluating Exploratory, Compositional, and Transformative Generalization
- NeurIPS 2025On Learning Verifiers and Implications to Chain-of-Thought Reasoning
- NeurIPS 2025On Reasoning Strength Planning in Large Reasoning Models
- NeurIPS 2025On the Bias of Next-Token Predictors Toward Systematically Inefficient Reasoning: A Shortest-Path Case Study
- NeurIPS 2025On the Effect of Negative Gradient in Group Relative Deep Reinforcement Optimization
- NeurIPS 2025Once Upon an Input: Reasoning via Per-Instance Program Synthesis
- NeurIPS 2025One Token Embedding Is Enough to Deadlock Your Large Reasoning Model
- NeurIPS 2025Open-Reasoner-Zero: An Open Source Approach to Scaling Up Reinforcement Learning on the Base Model
- NeurIPS 2025OpenCUA: Open Foundations for Computer-Use Agents
- NeurIPS 2025OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles
- NeurIPS 2025Optimizing Anytime Reasoning via Budget Relative Policy Optimization
- NeurIPS 2025Optimizing Chain-of-Thought Reasoners via Gradient Variance Minimization in Rejection Sampling and RL
- NeurIPS 2025OST-Bench: Evaluating the Capabilities of MLLMs in Online Spatio-temporal Scene Understanding
- NeurIPS 2025PAID: Pairwise Angular-Invariant Decomposition for Continual Test-Time Adaptation
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。