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 3,512 篇，第 24 / 71 页
- ICML 2026MIND: Multi-rationale INtegrated Discriminative Reasoning Framework for Multi-modal Large Models
- ICML 2026Mining Useful General Data for Low-Resource Domain Adaptation
- ICML 2026Mitigating Label Shift in Tabular In-Context Learning via Test-Time Posterior Adjustment
- ICML 2026Mitigating Premature Exploitation in Particle-based Monte Carlo for Inference-Time Scaling
- ICML 2026Mitigating the Safety–Utility Trade-off in LLM Alignment via Adaptive Safe Context Learning
- ICML 2026MixReasoning: Switching Modes to Think
- ICML 2026MLLM-4D: Towards Visual-based Spatial-Temporal Intelligence
- ICML 2026MME-Reasoning: A Broad-Spectrum Benchmark for Evaluating Logical Reasoning in MLLMs
- ICML 2026Modeling Hierarchical Thinking in Large Reasoning Models
- ICML 2026Models Under SCOPE: Scalable and Controllable Routing via Pre-hoc Reasoning
- ICML 2026Monitorability as a Free Gift: How RLVR Spontaneously Aligns Reasoning
- ICML 2026Monitoring Monitorability
- ICML 2026More Sail than Ballast: Addressing Harmful Knowledge Leakage in the Expansive Reasoning Space of LRMs
- ICML 2026Multi-Integration of Labels Across Categories for Component Identification in Multi-trial Time Series
- ICML 2026Multi-Objective Protein Design via Memory-Aware Test-Time Scaling in Diffusion Models
- ICML 2026Multimodal Fact-Level Attribution for Verifiable Reasoning
- ICML 2026Multimodal Function Vectors for Visual Relations
- ICML 2026MultiPriv: Benchmarking Individual-Level Privacy Reasoning in Vision-Language Models
- ICML 2026Neuro-Fuzzy Concept Learning for Interpretable Large Multimodal Models
- ICML 2026Noise-corrected GRPO: From Noisy Rewards to Unbiased Gradients
- ICML 2026Not All Invariants Are Equal: Curating Training Data to Accelerate Program Verification with SLMs
- ICML 2026Omni-Perception Policy Optimization for Multimodal Emotion Reasoning
- ICML 2026OmniVideo-R1: Reinforcing Audio-visual Reasoning with Query Intention and Modality Attention
- ICML 2026On Robustness and Chain-of-Thought Consistency of RL-Finetuned VLMs
- ICML 2026On the "Induction Bias" in Sequence Models
- ICML 2026On the Emergence of Implicit Curriculum in RLVR Learning Dynamics
- ICML 2026On the Generalization Gap in Self-Evolving Language Model Reasoning
- ICML 2026On the Interplay of Pre-Training, Mid-Training, and RL on Reasoning Language Models
- ICML 2026On the Intrinsic Limits of Transformer Image Embeddings in Non-Solvable Spatial Reasoning
- ICML 2026On the Limits of Test-Time Compute: Sequential Reward Filtering for Better Inference
- ICML 2026One Step Forward and K Steps Back: Better Reasoning with Denoising Recursion Models
- ICML 2026One-shot Entropy Minimization for Language Model Reasoning
- ICML 2026One-Way Policy Optimization for Self-Evolving LLMs
- ICML 2026Op-CAD: Benchmarking and Investigating Operation-oriented CAD Generation
- ICML 2026Open-o3-Video: Grounded Video Reasoning with Explicit Spatio-Temporal Evidence
- ICML 2026Open-World LLM Logical Reasoning
- ICML 2026OpenDeception: Learning Deception and Trust in Human–AI Interaction via Multi-Agent Simulation
- ICML 2026OpenHA: A Series of Open-Source Hierarchical Agentic Models in Minecraft
- ICML 2026OpenTSLM: Time-Series Language Models for Reasoning over Multivariate Medical Text- and Time-Series Data
- ICML 2026OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scaling
- ICML 2026Opt-Miner: Empowering Information-Seeking Agent with Tree-Guided Data Synthesis for Optimization Modeling
- ICML 2026Optimal Self-Consistency for Efficient Reasoning with Large Language Models
- ICML 2026Optimizing Inference-Time Compute for Medical Reasoning via Uncertainty Quantification
- ICML 2026Orchestrating Spatial Semantics via a Zone-Graph Paradigm for Intricate Indoor Scene Generation
- ICML 2026Out-of-Distribution Evaluation of Rule-Based and Strategic Reasoning in Chess Transformers
- ICML 2026Outcome Rewards Do Not Guarantee Verifiable or Causally Important Reasoning
- ICML 2026Overthinking: Amplifying Reasoning Weights to Extract Learned Secrets
- ICML 2026Panini: Continual Learning in Token Space via Structured Memory
- ICML 2026Parallel-Probe: Towards Efficient Parallel Thinking via 2D Probing
- ICML 2026PATRA: Pattern-Aware Alignment and Balanced Reasoning for Time Series Question Answering
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。