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 652 篇，第 7 / 14 页
- ICLR 2026Mapping Post-Training Forgetting in Language Models at Scale
- ICLR 2026Markovian Transformers for Informative Language Modeling
- ICLR 2026MARTI: A Framework for Multi-Agent LLM Systems Reinforced Training and Inference
- ICLR 2026Math Blind: Failures in Diagram Understanding Undermine Reasoning in MLLMs
- ICLR 2026MathFimer: Enhancing Mathematical Reasoning by Expanding Reasoning Steps through Fill-in-the-Middle Task
- ICLR 2026MathNet: A Global Multimodal Benchmark for Mathematical Reasoning and Retrieval
- ICLR 2026Measuring Audio's Impact on Correctness: Audio-Contribution-Aware Post-Training of Large Audio Language Models
- ICLR 2026Mechanistic Detection and Mitigation of Hallucination in Large Reasoning Models
- ICLR 2026Medical thinking with multiple images
- ICLR 2026MemGen: Weaving Generative Latent Memory for Self-Evolving Agents
- ICLR 2026Memory-T1: Reinforcement Learning for Temporal Reasoning in Multi-session Agents
- ICLR 2026MergePRAG: Orthogonal Merging of Passage-experts for Multi-hop Parametric RAG
- ICLR 2026MesaNet: Sequence Modeling by Locally Optimal Test-Time Training
- ICLR 2026MetaSpatial: Reinforcing 3D Spatial Reasoning in VLMs for the Metaverse
- ICLR 2026MIDAS: Multi-Image Dispersion and Semantic Reconstruction for Jailbreaking MLLMs
- ICLR 2026MILR: Improving Multimodal Image Generation via Test-Time Latent Reasoning
- ICLR 2026Mirage or Method? How Model–Task Alignment Induces Divergent RL Conclusions
- ICLR 2026Mixture-of-Visual-Thoughts: Exploring Context-Adaptive Reasoning Mode Selection for General Visual Reasoning
- ICLR 2026MM-HELIX: Boosting Multimodal Long-Chain Reflective Reasoning with Holistic Platform and Adaptive Hybrid Policy Optimization
- ICLR 2026MME-Emotion: A Holistic Evaluation Benchmark for Emotional Intelligence in Multimodal Large Language Models
- ICLR 2026MMR-Life: Piecing Together Real-life Scenes for Multimodal Multi-image Reasoning
- ICLR 2026MMR-V: What's Left Unsaid? A Benchmark for Multimodal Deep Reasoning in Videos
- ICLR 2026MMReD: a Cross-Modal Benchmark for Dense Context Reasoning
- ICLR 2026MMSI-Bench: A Benchmark for Multi-Image Spatial Intelligence
- ICLR 2026Mode-conditioning unlocks superior test-time compute scaling
- ICLR 2026MoDr: Mixture-of-Depth-Recurrent Transformers for Test-Time Reasoning
- ICLR 2026MoL: Adaptive Mixture-of-Length Reasoning for Efficient Question Answering with Context
- ICLR 2026MolecularIQ: Characterizing Chemical Reasoning Capabilities Through Symbolic Verification on Molecular Graphs
- ICLR 2026More Thought, Less Accuracy? On the Dual Nature of Reasoning in Vision-Language Models
- ICLR 2026MoReBench: Evaluating Procedural and Pluralistic Moral Reasoning in Language Models, More than Outcomes
- ICLR 2026Motion-R1: Enhancing Motion Generation with Decomposed Chain-of-Thought and RL Binding
- ICLR 2026mR3: Multilingual Rubric-Agnostic Reward Reasoning Models
- ICLR 2026MRMR: A Realistic and Expert-Level Multidisciplinary Benchmark for Reasoning-Intensive Multimodal Retrieval
- ICLR 2026MSCR: Exploring the Vulnerability of LLMs’ Mathematical Reasoning Abilities Using Multi-Source Candidate Replacement
- ICLR 2026Multiple Token Divergence: Measuring and Steering In-Context Computation Density
- ICLR 2026Multiverse Mechanica: A Testbed for Learning Game Mechanics via Counterfactual Worlds
- ICLR 2026Music Flamingo: Scaling Music Understanding in Audio Language Models
- ICLR 2026Native Reasoning Models: Training Language Models to Reason on Unverifiable Data
- ICLR 2026Nemotron-CC-Math: A 133 Billion-Token-Scale High Quality Math Pretraining Dataset
- ICLR 2026Nemotron-Research-Tool-N1: Exploring Tool-Using Language Models with Reinforced Reasoning
- ICLR 2026NEO — No-Optimization Test-Time Adaptation through Latent Re-Centering
- ICLR 2026NePTune: A Neuro-Pythonic Framework for Tunable Compositional Reasoning on Vision-Language
- ICLR 2026Neural Force Field: Few-shot Learning of Generalized Physical Reasoning
- ICLR 2026No Labels, No Problem: Training Visual Reasoners with Multimodal Verifiers
- ICLR 2026No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping
- ICLR 2026Not All Bits Are Equal: How Model Scale Changes Memory-Optimal Reasoning
- ICLR 2026Not Search, But Scan: Benchmarking MLLMs on Scan-Oriented Academic Paper Reasoning
- ICLR 2026Nudging the Boundaries of LLM Reasoning
- ICLR 2026OCR-Reasoning Benchmark: Unveiling the True Capabilities of MLLMs in Complex Text-Rich Image Reasoning
- ICLR 2026ODI-Bench: Can MLLMs Understand Immersive Omnidirectional Environments?
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。