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 49 / 71 页
- NeurIPS 2025GoT: Unleashing Reasoning Capability of MLLM for Visual Generation and Editing
- NeurIPS 2025GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning Chains
- NeurIPS 2025GRIP: A Graph-Based Reasoning Instruction Producer
- NeurIPS 2025GRIT: Teaching MLLMs to Think with Images
- NeurIPS 2025Grounded Reinforcement Learning for Visual Reasoning
- NeurIPS 2025GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning
- NeurIPS 2025GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents
- NeurIPS 2025GUI-Rise: Structured Reasoning and History Summarization for GUI Navigation
- NeurIPS 2025Guiding LLM Decision-Making with Fairness Reward Models
- NeurIPS 2025GVPO: Group Variance Policy Optimization for Large Language Model Post-Training
- NeurIPS 2025Heterogeneous Adversarial Play in Interactive Environments
- NeurIPS 2025Hogwild! Inference: Parallel LLM Generation via Concurrent Attention
- NeurIPS 2025HoloLLM: Multisensory Foundation Model for Language-Grounded Human Sensing and Reasoning
- NeurIPS 2025How do Transformers Learn Implicit Reasoning?
- NeurIPS 2025How Far Are We from Optimal Reasoning Efficiency?
- NeurIPS 2025Hybrid Latent Reasoning via Reinforcement Learning
- NeurIPS 2025HypoBootstrap: A Bootstrapping Framework for Inductive Reasoning
- NeurIPS 2025ICPC-Eval: Probing the Frontiers of LLM Reasoning with Competitive Programming Contests
- NeurIPS 2025Improving Formal Reasoning of Transformer with State Stack
- NeurIPS 2025Incentivizing Dual Process Thinking for Efficient Large Language Model Reasoning
- NeurIPS 2025Incentivizing LLMs to Self-Verify Their Answers
- NeurIPS 2025Incentivizing Reasoning for Advanced Instruction-Following of Large Language Models
- NeurIPS 2025Ineq-Comp: Benchmarking Human-Intuitive Compositional Reasoning in Automated Theorem Proving of Inequalities
- NeurIPS 2025Inference-Time Hyper-Scaling with KV Cache Compression
- NeurIPS 2025InstructHOI: Context-Aware Instruction for Multi-Modal Reasoning in Human-Object Interaction Detection
- NeurIPS 2025Interpreting Arithmetic Reasoning in Large Language Models using Game-Theoretic Interactions
- NeurIPS 2025Introducing FOReCAst: The Future Outcome Reasoning and Confidence Assessment Benchmark
- NeurIPS 2025Is PRM Necessary? Problem-Solving RL Implicitly Induces PRM Capability in LLMs
- NeurIPS 2025JarvisArt: Liberating Human Artistic Creativity via an Intelligent Photo Retouching Agent
- NeurIPS 2025Jury-and-Judge Chain-of-Thought for Uncovering Toxic Data in 3D Visual Grounding
- NeurIPS 2025K-DeCore: Facilitating Knowledge Transfer in Continual Structured Knowledge Reasoning via Knowledge Decoupling
- NeurIPS 2025Kinetics: Rethinking Test-Time Scaling Law
- NeurIPS 2025Knot So Simple: A Minimalistic Environment for Spatial Reasoning
- NeurIPS 2025Know What You Don't Know: Uncertainty Calibration of Process Reward Models
- NeurIPS 2025KRIS-Bench: Benchmarking Next-Level Intelligent Image Editing Models
- NeurIPS 2025KTAE: A Model-Free Algorithm to Key-Tokens Advantage Estimation in Mathematical Reasoning
- NeurIPS 2025Language Models Can Predict Their Own Behavior
- NeurIPS 2025Language Models can Self-Improve at State-Value Estimation for Better Search
- NeurIPS 2025Large Language Models as End-to-end Combinatorial Optimization Solvers
- NeurIPS 2025Large language models can learn and generalize steganographic chain-of-thought under process supervision
- NeurIPS 2025Large Language Models Think Too Fast To Explore Effectively
- NeurIPS 2025LASeR: Learning to Adaptively Select Reward Models with Multi-Arm Bandits
- NeurIPS 2025Latent Chain-of-Thought for Visual Reasoning
- NeurIPS 2025Latent Principle Discovery for Language Model Self-Improvement
- NeurIPS 2025LayerCraft: Enhancing Text-to-Image Generation with CoT Reasoning and Layered Object Integration
- NeurIPS 2025LCDB 1.1: A Database Illustrating Learning Curves Are More Ill-Behaved Than Previously Thought
- NeurIPS 2025Learning long range dependencies through time reversal symmetry breaking
- NeurIPS 2025Learning to Better Search with Language Models via Guided Reinforced Self-Training
- NeurIPS 2025Learning to Focus: Causal Attention Distillation via Gradient‐Guided Token Pruning
- NeurIPS 2025Learning to Reason under Off-Policy Guidance
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。