推理模型论文趋势 2023–2026

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。

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 361 篇，第 1 / 8 页

1. NeurIPS 2026A Batched Hartigan's $k$-Means Clustering
2. NeurIPS 2026A Diagnostic Benchmark for Layered Layout and Template-Variant Reasoning
3. NeurIPS 2026A Mechanistic Analysis of Looped Reasoning Language Models
4. NeurIPS 2026A Solvable Model of Chain-of-Thought in In-Context Learning
5. NeurIPS 2026A Theory of Online Learning with Autoregressive Chain-of-Thought Reasoning
6. NeurIPS 2026A Tight Hierarchy For Chain of Thought
7. NeurIPS 2026A$^3$Bench: A Benchmark for Compositional Reasoning over Aggressive Interactions in Videos
8. NeurIPS 2026Activation Functions Shape Token Synchronization in Stochastic Transformer Dynamics
9. NeurIPS 2026Active Probabilistic Reasoning in Humans and LLMs
10. NeurIPS 2026AdaKVQ: Adaptive Mixed-Precision KV Cache Quantization For Efficient Reasoning Models
11. NeurIPS 2026Adapting in the Dark: Efficient and Stable Test-Time Adaptation for Black-Box Models
12. NeurIPS 2026Adversarially Attacking Symbolic Vocabulary Vulnerabilities In LLM Planners
13. NeurIPS 2026Agents as Neuro-Symbolic Reasoners: Path Feasibility Reasoning for Precise Static Bug Detection
14. NeurIPS 2026AI Models Can Provably Hide Arbitrary Capabilities
15. NeurIPS 2026AirIAD: Agentic Iterative Reasoning for Industrial Anomaly Detection
16. NeurIPS 2026ALTER: An Allen's Algebra-Based Evaluation Framework for Temporal Reasoning of LLMs
17. NeurIPS 2026An Enigma of Artificial Reason: Investigating the Production-Evaluation Gap in Large Reasoning Models
18. NeurIPS 2026ANCHOR: Audio-Visually Grounded Chain-of-Thought Reasoning Benchmark
19. NeurIPS 2026Anchoring Reasoning Distillation via Syntactic Constraints
20. NeurIPS 2026Anti-Self-Distillation for Reasoning RL via Pointwise Mutual Information
21. NeurIPS 2026Anymotion: A Dataset, Benchmark, and Baseline for Controllable Human Motion Editing
22. NeurIPS 2026Anytime-Valid PAC-Bayes Certificates for Adaptive Test-Time Scaling
23. NeurIPS 2026Argument Graph Uncertainty: Quantifying Uncertainty from the Logical Structure of Reasoning Chains
24. NeurIPS 2026Attention Drift: What Auto-Regressive Speculative Decoding Models Learn
25. NeurIPS 2026Attention-based PCA
26. NeurIPS 2026AURA: An Autonomous Retouching Agent with Photographic Visual Thinking
27. NeurIPS 2026AutoDataBench: How Far Are LLM Agents from Autonomously Engineering Post-Training Data Pipelines?
28. NeurIPS 2026AVIS: Adaptive Test-Time Scaling for Vision–Language Models
29. NeurIPS 2026Bayesian Test-Time Inference of Task-Aligned Similarity from Weak Interactive Feedback
30. NeurIPS 2026Before It Fades: Reinforcing Temporal Representations at Inference Time in VideoLLMs
31. NeurIPS 2026Bernini: Latent Semantic Planning for Video Diffusion
32. NeurIPS 2026Best Arm Identification in Generalized Linear Bandits via Hybrid Feedback
33. NeurIPS 2026Beyond [SEG] Tokens: Training-Free Video Reasoning Segmentation via Counterfactual Inference and Contrastive Concept
34. NeurIPS 2026Beyond Ground Truth: Evaluating Non-Verifiable Reasoning in LLMs through Moral Robustness
35. NeurIPS 2026Beyond What Seems Necessary: Hidden Gains from Scaling Training-Time Reasoning Length under Outcome Supervision
36. NeurIPS 2026Bias-Variance Optimized Preference Optimization for Large Reasoning Models
37. NeurIPS 2026Bits Beat Tokens: A Regret Rate Distortion Theory for Large Language Model Agents
38. NeurIPS 2026Block Sparse Flash Attention
39. NeurIPS 2026Boosting Inference with Guided Reasoning: Stochastic Exploration for Recursive Models
40. NeurIPS 2026Boule or Baguette? A Study on Task Topology, Length Generalization, and the Benefit of Reasoning Trace
41. NeurIPS 2026BrainCoT: A Multi-Task Zero-Shot Brain Signal Foundation Model with Neurometric-Anchored Chain-of-Thought Reasoning
42. NeurIPS 2026Bridging Compute- and Data-Optimal Pretraining
43. NeurIPS 2026Bridging Structure and Language: Graph-Based Visual Reasoning for Autonomous Road Understanding
44. NeurIPS 2026CaC: Advancing Video Reward Models via Hierarchical Spatiotemporal Concentrating
45. NeurIPS 2026CausalSpatial: A Benchmark for Object-Centric Causal Spatial Reasoning
46. NeurIPS 2026CellularS2-Bench: A Staged, Evidence-Grounded Benchmark for Cellular Network Security Reasoning
47. NeurIPS 2026Chain-of-Thought Is Not Explainability
48. NeurIPS 2026ChainSpace: A Chained-Reasoning Paradigm for Spatial Intelligence
49. NeurIPS 2026ChartArena: A Unified Benchmark with Atomic-Primitive Reasoning for Chart Parsing
50. NeurIPS 2026CineMME: Benchmarking Fine-Grained Perception and Plot Reasoning in Multimodal Large Language 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。