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 14 / 71 页
- ICLR 2026Reverse-Engineered Reasoning for Open-Ended Generation
- ICLR 2026Revisual-R1: Advancing Multimodal Reasoning From Optimized Cold Start to Staged Reinforcement Learning
- ICLR 2026RewardMap: Tackling Sparse Rewards in Fine-grained Visual Reasoning via Multi-Stage Reinforcement Learning
- ICLR 2026ReWatch-R1: Boosting Complex Video Reasoning in Large Vision-Language Models through Agentic Data Synthesis
- ICLR 2026Rex-Thinker: Grounded Object Referring via Chain-of-Thought Reasoning
- ICLR 2026RFEval: Benchmarking Reasoning Faithfulness under Counterfactual Reasoning Intervention in Large Reasoning Models
- ICLR 2026RL for Reasoning by Adaptively Revealing Rationales
- ICLR 2026RL of Thoughts: Navigating LLM Reasoning with Inference-time Reinforcement Learning
- ICLR 2026RL Squeezes, SFT Expands: A Comparative Study of Reasoning LLMs
- ICLR 2026RLAD: Training LLMs to Discover Abstractions for Solving Reasoning Problems
- ICLR 2026RLP: Reinforcement as a Pretraining Objective
- ICLR 2026RM-R1: Reward Modeling as Reasoning
- ICLR 2026Robust Test-time Video-Text Retrieval: Benchmarking and Adapting for Query Shifts
- ICLR 2026ROVER: Benchmarking Reciprocal Cross-Modal Reasoning for Omnimodal Generation
- ICLR 2026RPM: Reasoning-Level Personalization for Black-Box Large Language Models
- ICLR 2026RuleReasoner: Reinforced Rule-based Reasoning via Domain-aware Dynamic Sampling
- ICLR 2026Sample More to Think Less: Group Filtered Policy Optimization for Concise Reasoning
- ICLR 2026Sample Smart, Not Hard: Correctness-First Decoding for Better Reasoning in LLMs
- ICLR 2026Scaf-GRPO: Scaffolded Group Relative Policy Optimization for Enhancing LLM Reasoning
- ICLR 2026Scalable Chain of Thoughts via Elastic Reasoning
- ICLR 2026Scaling Atomistic Protein Binder Design with Generative Pretraining and Test-Time Compute
- ICLR 2026Scaling Linear Attention with Sparse State Expansion
- ICLR 2026Scaling Reasoning Hop Exposes Weaknesses: Demystifying and Improving Hop Generalization in Large Language Models
- ICLR 2026Scaling Up, Speeding Up: A Benchmark of Speculative Decoding for Efficient LLM Test-Time Scaling
- ICLR 2026SceneCOT: Eliciting Chain-of-Thought Reasoning in 3D Scenes
- ICLR 2026SCoT: Teaching 3D-LLMs to Think Spatially with Million-scale CoT Annotations
- ICLR 2026SealQA: Raising the Bar for Reasoning in Search-Augmented Language Models
- ICLR 2026Seeing Across Views: Benchmarking Spatial Reasoning of Vision-Language Models in Robotic Scenes
- ICLR 2026Seek-CAD: A Self-refined Generative Modeling for 3D Parametric CAD Using Local Inference via DeepSeek
- ICLR 2026Segment-Level Attribution for Selective Learning of Long Reasoning Traces
- ICLR 2026Selection, Reflection and Self-Refinement: Revisit Reasoning Tasks via a Causal Lens
- ICLR 2026Self-Jailbreaking: Language Models Can Reason Themselves Out of Safety Alignment After Benign Reasoning Training
- ICLR 2026Self-Refining Vision Language Model for Robotic Failure Detection and Reasoning
- ICLR 2026SesaHand: Enhancing 3D Hand Reconstruction via Controllable Generation with Semantic and Structural Alignment
- ICLR 2026SIM-CoT: Supervised Implicit Chain-of-Thought
- ICLR 2026SimpleToM: Exposing the Gap between Explicit ToM Inference and Implicit ToM Application in LLMs
- ICLR 2026SimuHome: A Temporal- and Environment-Aware Benchmark for Smart Home LLM Agents
- ICLR 2026SketchThinker-R1: Towards Efficient Sketch-Style Reasoning in Large Multimodal Models
- ICLR 2026SkillFactory: Self-Distillation for Learning Cognitive Behaviors
- ICLR 2026SLM-MUX: Orchestrating Small Language Models for Reasoning
- ICLR 2026Slow-Fast Policy Optimization: Reposition-Before-Update for LLM Reasoning
- ICLR 2026Small Drafts, Big Verdict: Information-Intensive Visual Reasoning via Speculation
- ICLR 2026SMAN-Bench: A Cross-System Benchmark for Mobile Agents under Single- and Multi-path, Ambiguous, and Noisy Tasks
- ICLR 2026Smarter Not Harder: Generative Process Evaluation with Intrinsic-Signal Driving and Ability‑Adaptive Reward Shaping
- ICLR 2026Soft Tokens, Hard Truths
- ICLR 2026Softmax Transformers are Turing-Complete
- ICLR 2026SophiaVL-R1: Reinforcing MLLMs Reasoning with Thinking Reward
- ICLR 2026SpaCE-Eval: A Benchmark for Real-World Multi-Modal Reasoning
- ICLR 2026Sparse Attention Adaptation for Long Reasoning
- ICLR 2026Spatial CAPTCHA: Generatively Benchmarking Spatial Reasoning for Human-Machine Differentiation
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。