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 31 / 36 页
- NeurIPS 2026Confidence Estimation via Decoupled Smoothing for Dynamic LLM Routing and Aggregation
- NeurIPS 2026Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning
- NeurIPS 2026Consilience for Verifier-Free Test-Time Scaling
- NeurIPS 2026Consolidating Reasoning with Test-Time Learning
- NeurIPS 2026Context-Aware Autoregressive Image Generation for Emerging Reasoning Properties
- NeurIPS 2026Contractive Restoring Flows: Robust Reasoning Distillation via Orbital Stability
- NeurIPS 2026Contrastive Thinking Decoding: Steering Answer Generation in Reasoning Models
- NeurIPS 2026ControlJEPA: Principled Trajectory Regularization via Lyapunov Tube Loss
- NeurIPS 2026Controlling Temporal Pseudo-Label Marginals for Stable Online Test-Time Adaptation
- NeurIPS 2026Convex Compositional Reasoning Models
- NeurIPS 2026CoQuant: Covariance-Aware Rotation for 2-bit KV Cache Quantization
- NeurIPS 2026CoRE-RL: Co-evolving Reasoning Trajectories and Evidence Subgraphs with Learned Evidence Projection
- NeurIPS 2026Correct but Unselectable: The Hidden Interface Tax in Multi-Candidate Reasoning
- NeurIPS 2026Corrupted Plans, Clean Traces: What Planning-Execution Decoupling Reveals About CoT Monitoring
- NeurIPS 2026CoT-Guard: Small Models for Strong Monitoring
- NeurIPS 2026CoTs as Probabilistic Programs: A Programmatic View of Thinking Step-by-Step in Language Models
- NeurIPS 2026CoWorld-VLA: Thinking in a Multi-Expert World Model for Autonomous Driving
- NeurIPS 2026CRANE: Constrained Reasoning Injection for Code Agents via Nullspace Editing
- NeurIPS 2026Cross-Channel Agreement Beats Consensus: Compositional Verification for Geometry Reasoning
- NeurIPS 2026Curriculum proof repair with learned counterexamples
- NeurIPS 2026Data Diversity Drives the Emergence of Symbolic Mechanisms Supporting Abstract Reasoning
- NeurIPS 2026Decoding the Critique Mechanism in Large Reasoning Models
- NeurIPS 2026Decoupled Descent: Exact Test Error Tracking Via Approximate Message Passing
- NeurIPS 2026DeltaPrompts: Escaping the Zero-Delta Trap in Multimodal Distillation
- NeurIPS 2026Deployment-Memory LLM Test-Time Training Should Require Behavioral Evidence Beyond Perplexity
- NeurIPS 2026Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves
- NeurIPS 2026Detect What You Need: Chain-of-Causal Reasoning for 3D Intent Grounding
- NeurIPS 2026Diffusion Thinking for Fast Long-Form Spatial Reasoning in Vision--Language Models
- NeurIPS 2026Distilling LLM Feedback for Lean Theorem Proving
- NeurIPS 2026Do Deep Networks Forget Initialization? A Forgetting-Time View of Practical Inductive Bias
- NeurIPS 2026Do Reasoning LLMs Refuse What They Infer in Long Contexts?
- NeurIPS 2026Do Thinking Tokens Help with Safety?
- NeurIPS 2026Does This Gradient Spark Joy?
- NeurIPS 2026Early Signals, Strong Decisions: Prefix-Guided Sampling for Parallel Test-Time Scaling
- NeurIPS 2026ECG-Reasoning-Benchmark: A Benchmark for Evaluating Clinical Reasoning Capabilities in ECG Interpretation
- NeurIPS 2026Efficient Reasoning via Constrained Optimization in Latent Space
- NeurIPS 2026Efficiently Representing Algorithms With Chain-of-Thought Transformers
- NeurIPS 2026EmpathyChat: Structured Cognitive Reasoning in Empathetic Spoken Dialogue
- NeurIPS 2026EndoSCOP-V: A Multi-Turn Video Understanding Evaluation Framework for Multimodal Models in Endoscopy Reporting and Clinical Reasoning
- NeurIPS 2026Enhancing LLMs with Cognitive-Affective Personality Inference for Simulating Human Social-Psychological Behavior
- NeurIPS 2026EntropyCache: Decoded Token Entropy Guided KV Caching for Diffusion Language Models
- NeurIPS 2026Escaping Reasoning Basins: Basin-Aware Search for Inference-Time LLM Reasoning
- NeurIPS 2026Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models
- NeurIPS 2026ESENSC: A Polynomial-Time Axiomatic Alternative to SHAP
- NeurIPS 2026EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample
- NeurIPS 2026Evaluating Test-Time Scaling of General LLM Agents
- NeurIPS 2026Evaluating Whether LLMs Can Reliably Connect the DOTs?
- NeurIPS 2026Evaluation Awareness in Language Models Has Limited Effect on Behaviour
- NeurIPS 2026EventPrune: Cascaded Event-Assisted Token Pruning for Efficient First-Person Dynamic Spatial Reasoning
- NeurIPS 2026Exact Flow Linear Attention: Exact Solution from Continuous-Time Dynamics
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。