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 4 / 14 页
- ICLR 2026Error Notebook-Guided, Training-Free Part Retrieval in 3D CAD Assemblies via Vision-Language Models
- ICLR 2026Evaluating Language Models' Evaluations of Games
- ICLR 2026EvolProver: Advancing Automated theorem proving by Evolving Formalized Problems via Symmetry and Difficulty
- ICLR 2026ExGRPO: Learning to Reason from Prior Successes
- ICLR 2026Expanding Reasoning Potential in Foundation Model by Learning Diverse Chains of Thought Patterns
- ICLR 2026Explain in Your Own Words: Improving Reasoning via Token-Selective Dual Knowledge Distillation
- ICLR 2026Explainable LLM Unlearning through Reasoning
- ICLR 2026Exploration vs Exploitation: Rethinking RLVR through Clipping, Entropy, and Spurious Reward
- ICLR 2026Explore-on-Graph: Incentivizing Autonomous Exploration of Large Language Models on Knowledge Graphs with Path-refined Reward Modeling
- ICLR 2026Exploring the Limits of Sub-Billion Language Model Reasoners with Open Training Recipes
- ICLR 2026ExPO-HM: Learning to Explain-then-Detect for Hateful Meme Detection
- ICLR 2026Exposing Mixture and Annotating Confusion for Active Universal Test-Time Adaptation
- ICLR 2026Exposing Weaknesses of Large Reasoning Models through Graph Algorithm Problems
- ICLR 2026Factuality Matters: When Image Generation and Editing Meet Structured Visuals
- ICLR 2026FaithCoT-Bench: Benchmarking Instance-Level Faithfulness of Chain-of-Thought Reasoning
- ICLR 2026Faithful Bi-Directional Model Steering via Distribution Matching and Distributed Interchange Interventions
- ICLR 2026FAPO: Flawed-Aware Policy Optimization for Efficient and Reliable Reasoning
- ICLR 2026FATE: A Formal Benchmark Series for Frontier Algebra of Multiple Difficulty Levels
- ICLR 2026Fine-R1: Make Multi-modal LLMs Excel in Fine-Grained Visual Recognition by Chain-of-Thought Reasoning
- ICLR 2026FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning
- ICLR 2026Fixing the Broken Compass: Diagnosing and Improving Inference-Time Reward Modeling
- ICLR 2026Flash-Searcher: Fast and Effective Web Agents via DAG-Based Parallel Execution
- ICLR 2026FlowGen: Synthesizing Diverse Flowcharts to Enhance and Benchmark MLLM Reasoning
- ICLR 2026FlowRL: Matching Reward Distributions for LLM Reasoning
- ICLR 2026FlowSearcher: Synthesizing Memory-Guided Agentic Workflows for Web Information Seeking
- ICLR 2026FLUX-Reason-6M & PRISM-Bench: A Million-Scale Text-to-Image Reasoning Dataset and Comprehensive Benchmark
- ICLR 2026Following the Navigation: Enhancing Small Language Models Contextual Reasoning with LLM Guidance
- ICLR 2026FrameThinker: Learning to Think with Long Videos via Multi-Turn Frame Spotlighting
- ICLR 2026FREAK: A Fine-grained Hallucination Evaluation Benchmark for Advanced MLLMs
- ICLR 2026Frequency-Domain Better than Time-Domain for Causal Structure Recovery in Dynamical Systems on Networks
- ICLR 2026FRIEDA: Benchmarking Multi-Step Cartographic Reasoning in Vision-Language Models
- ICLR 2026From Abstract to Contextual: What LLMs Still Cannot Do in Mathematics
- ICLR 2026From Broad Exploration to Stable Synthesis: Entropy-Guided Optimization for Autoregressive Image Generation
- ICLR 2026From f(x) and g(x) to f(g(x)): LLMs Learn New Skills in RL by Composing Old Ones
- ICLR 2026From Five Dimensions to Many: Large Language Models as Precise and Interpretable Psychological Profilers
- ICLR 2026From Large to Small: Transferring CUDA Optimization Expertise via Reasoning Graph
- ICLR 2026From Narrow to Panoramic Vision: Attention-Guided Cold-Start Reshapes Multimodal Reasoning
- ICLR 2026From Seeing to Doing: Bridging Reasoning and Decision for Robotic Manipulation
- ICLR 2026Front-Loading Reasoning: The Synergy between Pretraining and Post-Training Data
- ICLR 2026FROST: Filtering Reasoning Outliers with Attention for Efficient Reasoning
- ICLR 2026FrugalRAG: Less is More in RL Finetuning for Multi-hop Question Answering
- ICLR 2026Frustratingly Simple Retrieval Improves Challenging, Reasoning-Intensive Benchmarks
- ICLR 2026Generalizable End-to-End Tool-Use RL with Synthetic CodeGym
- ICLR 2026Generalization of RLVR Using Causal Reasoning as a Testbed
- ICLR 2026Generalized Parallel Scaling with Interdependent Generations
- ICLR 2026GeoBench: Rethinking Multimodal Geometric Problem-Solving via Hierarchical Evaluation
- ICLR 2026GeoGramBench: Benchmarking the Geometric Program Reasoning in Modern LLMs
- ICLR 2026Get RICH or Die Scaling: Profitably Trading Inference Compute for Robustness
- ICLR 2026GHOST: Hallucination-Inducing Image Generation for Multimodal LLMs
- ICLR 2026GIQ: Benchmarking 3D Geometric Reasoning of Vision Foundation Models with Simulated and Real Polyhedra
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。