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 913 篇，第 11 / 19 页
- ICML 2026Think Deep, Not Just Long: Measuring LLM Reasoning Effort via Deep-Thinking Tokens
- ICML 2026Think in Latent, Explain in Language: Self-Explainable Latent Reasoning
- ICML 2026Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models
- ICML 2026Think Twice Before You Act: Enhancing Agent Behavioral Safety with Thought Correction
- ICML 2026Think-at-Hard: Selective Latent Iterations to Improve Reasoning Language Models
- ICML 2026Think-Then-Generate: Reasoning-Aware Text-to-Image Diffusion with LLM Encoders
- ICML 2026Thinking in Flow: A Dissipative Stabilization Operator for Robust Autoregressive Reasoning
- ICML 2026Thinking in Latent Space: Progressive Multimodal Simplification for Visual Reasoning
- ICML 2026Thinking in Scales: Accelerating Gigapixel Pathology Image Analysis via Adaptive Continuous Reasoning
- ICML 2026Thinking in Structures: Evaluating Spatial Intelligence in Constraint-Governed Spaces
- ICML 2026Thoughtbubbles: an Unsupervised Method for Parallel Thinking in Latent Space
- ICML 2026ThoughtFold: Folding Reasoning Chains via Introspective Preference Learning
- ICML 2026ThreadWeaver: Adaptive Threading for Efficient Parallel Reasoning in Language Models
- ICML 2026Time Series Reasoning via Process-Verifiable Thinking Data Synthesis and Scheduling for Tailored LLM Reasoning
- ICML 2026TimeOmni-VL: Unified Models for Time Series Understanding and Generation
- ICML 2026TimeSpot: Benchmarking Geo-Temporal Understanding in Vision–Language Models in Real-World Settings
- ICML 2026Topological Active Inference for Task Disambiguation
- ICML 2026Toward Culturally Aligned LLMs through Ontology-Guided Multi-Agent Reasoning
- ICML 2026Toward Cybersecurity-Expert Small Language Models
- ICML 2026Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression
- ICML 2026Towards Feedback-to-Plan Decisions for Self-Evolving LLM Agents in CUDA Kernel Generation
- ICML 2026Towards Long-Horizon Interpretability: Efficient and Faithful Multi-Token Attribution for Reasoning LLMs
- ICML 2026Towards On-Policy SFT: Distribution Discriminant Theory and its Applications in LLM Training
- ICML 2026Towards One-to-Many Temporal Grounding
- ICML 2026TRACE: Toulmin-based Reasoning Assessment through Constructive Elements for LLM CoT Evaluation
- ICML 2026TRACER: Trajectory Risk Aggregation for Critical Episodes in Agentic Reasoning
- ICML 2026Training-Trajectory-Aware Token Selection
- ICML 2026Transformers with RL or SFT Provably Learn Sparse Boolean Functions, But Differently
- ICML 2026TRAP: Hijacking VLA CoT-Reasoning via Adversarial Patches
- ICML 2026TreePO: Enhancing Policy Efficacy and Inference Efficiency with Tree Modeling
- ICML 2026TriAttention: Efficient Long Reasoning with Trigonometric KV Compression
- ICML 2026TrustworthyQENN: A Quantum Evidential Neural Network Based on Complex-Valued Contrastive Learning for Uncertainty Pattern Classification
- ICML 2026Truthfulness Does Not Scale Like Reasoning: Why Polling Fails as a Proxy Verifier
- ICML 2026TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models
- ICML 2026Turbo Connection: Reasoning as Information Flow from Higher to Lower Layers
- ICML 2026Turning Drift into Constraint: Robust Reasoning Alignment in Non-Stationary Multi-Stream Environments
- ICML 2026TVI-CoT: Text-Visual Interleaved Chain-of-Thought Reasoning for Multimodal Understanding
- ICML 2026UFO: Chain-of-Evaluation for Omni-Condition Alignment in Multi-Modal Image Generation
- ICML 2026Unbiased Dynamic Pruning for Efficient Group-Based Policy Optimization
- ICML 2026Uncovering the Gradient Geometry of Long CoT: A Spectral-guided Approach to Reasoning Distillation
- ICML 2026Understanding Dynamic Compute Allocation in Recurrent Transformers
- ICML 2026UniCode: Augmenting Evaluation for Code Reasoning
- ICML 2026UniScale: Adaptive Unified Inference Scaling via Online Joint Optimization of Model Routing and Test-Time Scaling
- ICML 2026Universal Reasoner: A Single, Composable Plug-and-Play Reasoner for Frozen LLMs
- ICML 2026Unveiling the Entropy Dynamics of Chain-of-Thought Reasoning
- ICML 2026Unveiling the Structure of Do-Calculus Reasoning via Derivation Graphs
- ICML 2026USE: A Unified Self-Ensembling Framework for Test-Time Prompt Tuning
- ICML 2026V-ABS: Action-Observer Driven Beam Search for Dynamic Visual Reasoning
- ICML 2026V1: Unifying Generation and Self-Verification for Parallel Reasoners
- ICML 2026VAnim: Rendering-Aware Sparse State Modeling for Structure-Preserving Vector Animation
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。