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 25 / 36 页
- ICML 2026Persona2Web: Benchmarking Personalized Web Agents for Contextual Reasoning with User History
- ICML 2026PESD-TSF: A Period-Aware and Explicit Structured Decomposition Framework for Long-Term Time Series Forecasting
- ICML 2026Pessimistic Verification for Open-Ended Math Questions
- ICML 2026PETS: A Principled Framework Towards Optimal Trajectory Allocation for Efficient Test-Time Self-Consistency
- ICML 2026Plan Then Action: High-Level Planning Guidance Reinforcement Learning for LLM Reasoning
- ICML 2026PLANTAIN: Plan-Answer Interleaved Reasoning
- ICML 2026POLIA: Policy Optimization with Visual-Object-Level Intrinsic Advantage for Multimodal Reasoning
- ICML 2026PonderLM-2: Pretraining LLM with Latent Thoughts in Continuous Space
- ICML 2026Practical and Scalable Hamiltonian Monte Carlo Without the Metropolis Test
- ICML 2026Predicting Large Model Test Losses with a Noisy Quadratic System
- ICML 2026Prioritize the Process, Not Just the Outcome: Rewarding Latent Thought Trajectories Improves Reasoning in Looped Language Models
- ICML 2026Private and Stable Test-time Adaptation with Differential Privacy
- ICML 2026Privileged Information Distillation for Language Models
- ICML 2026ProbeLLM: Automating Principled Diagnosis of LLM Failures
- ICML 2026Probing How Scalable Table Data Enhances General Long-Context Reasoning
- ICML 2026Procedural Pretraining: Warming Up Language Models with Abstract Data
- ICML 2026Process Reward Agents for Steering Knowledge-Intensive Reasoning
- ICML 2026PromptDyG: Test-Time Prompt Adaptation on Dynamic Graphs
- ICML 2026Provable Benefits of RLVR over SFT for Reasoning Models: Learning to Backtrack Efficiently
- ICML 2026Provable Sample Efficiency of Curriculum Post-Training for Transformer Reasoning
- ICML 2026PRPO: Paragraph-level Policy Optimization for Vision-Language Deepfake Detection
- ICML 2026Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
- ICML 2026QEDBench: Quantifying the Alignment Gap in Automated Evaluation of University-Level Mathematical Proofs
- ICML 2026R-Diverse: Mitigating Diversity Illusion in Self-Play LLM Training
- ICML 2026R$^3$L: Reasoning 3D Layouts from Relative Spatial Relations
- ICML 2026R2-Router: A New Paradigm for LLM Routing with Reasoning
- ICML 2026Rational Transductors
- ICML 2026Re-FORC: Adaptive Reward Prediction for Efficient Chain-of-Thought Reasoning
- ICML 2026RE-TRAC: REcursive TRAjectory Compression for Deep Search Agents
- ICML 2026ReaForest: Fostering Generative Video Reasoning for Spatial Planning
- ICML 2026Real-Time Monitoring and Calibration of Chain-of-Thought Sycophancy in Large Reasoning Models
- ICML 2026Real-Time Visual Attribution Streaming in Thinking Model
- ICML 2026REALISTA: Realistic Latent Adversarial Attacks that Elicit LLM Hallucinations
- ICML 2026REAR: Test-time Preference Realignment through Reward Decomposition
- ICML 2026Reason with Thumbnails, Answer with Focus: An Efficient and Effective Paradigm for Multimodal Grounded Visual Reasoning
- ICML 2026Reason, Then Re-reason: Cross-view Revisiting Improves Spatial Reasoning
- ICML 2026ReasonEdit: Editing Vision--Language Models using Human Reasoning
- ICML 2026Reasoning about Reasoning: BAPO Bounds on Chain-of-Thought Token Complexity in LLMs
- ICML 2026Reasoning as an Attack Surface: Adaptive Evolutionary CoT Jailbreaks for LLMs
- ICML 2026Reasoning Cache: Continual Improvement Over Long Horizons via Short-Horizon RL
- ICML 2026Reasoning Can Be Restored by Correcting a Few Decision Tokens
- ICML 2026Reasoning Compartmentalization: Bridging the Concretization Gap via Abstraction-based Routing
- ICML 2026Reasoning LLM Improves Speaker Recognition in Long-form TV Dramas
- ICML 2026Reasoning Models Are Test Exploiters: Rethinking Multiple Choice
- ICML 2026Reasoning Models Struggle to Control their Chains of Thought
- ICML 2026Reasoning on the Manifold: Bidirectional Consistency for Self-Verification in Diffusion Language Models
- ICML 2026Reasoning over Boundaries: Enhancing Specification Alignment via Test-time Deliberation
- ICML 2026Reasoning Quality Emerges Early: Data Curation for Reasoning Models
- ICML 2026Reasoning Structure of Large Language Models
- ICML 2026Reasoning Theater: Disentangling Model Beliefs from Chain-of-Thought
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。