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 996 篇，第 1 / 20 页

1. ICLR 2026$\nabla$-Reasoner: LLM Reasoning via Test-Time Gradient Descent in Textual Space
2. ICLR 2026$\textbf{Re}^{2}$: Unlocking LLM Reasoning via Reinforcement Learning with Re-solving
3. ICLR 2026$AutoDrive\text{-}P^3$: Unified Chain of Perception–Prediction–Planning Thought via Reinforcement Fine-Tuning
4. ICLR 20263D Aware Region Prompted Vision Language Model
5. ICLR 2026A Balanced Neuro-Symbolic Approach for Commonsense Abductive Logic
6. ICLR 2026A Fano-Style Accuracy Upper Bound for LLM Single-Pass Reasoning in Multi-Hop QA
7. ICLR 2026A Simple "Motivation" Can Enhance Reinforcement Finetuning of Large Reasoning Models
8. ICLR 2026A State-Transition Framework for Efficient LLM Reasoning
9. ICLR 2026A$^2$FM: An Adaptive Agent Foundation Model for Tool-Aware Hybrid Reasoning
10. ICLR 2026ACADREASON: Exploring the Limits of Reasoning Models with Academic Research Problems
11. ICLR 2026AceReason-Nemotron 1.1: Advancing Math and Code Reasoning through SFT and RL Synergy
12. ICLR 2026ACPBench Hard: Unrestrained Reasoning about Action, Change, and Planning
13. ICLR 2026Actions as Language: Fine-Tuning VLMs into VLAs Without Catastrophic Forgetting
14. ICLR 2026Actions Speak Louder than Prompts: A Large-Scale Study of LLMs for Graph Inference
15. ICLR 2026ActivationReasoning: Logical Reasoning in Latent Activation Spaces
16. ICLR 2026Adaptive Social Learning via Mode Policy Optimization for Language Agents
17. ICLR 2026Adaptive Thinking: Large Language Models Know When to Think in Latent Space
18. ICLR 2026AdvChain: Adversarial Chain-of-Thought Tuning for Robust Safety Alignment of Large Reasoning Models
19. ICLR 2026AetherCode: Evaluating LLMs’ Ability to Win In Premier Programming Competitions
20. ICLR 2026Agent-X: Evaluating Deep Multimodal Reasoning in Vision-Centric Agentic Tasks
21. ICLR 2026Agentic Reinforced Policy Optimization
22. ICLR 2026AgentMath: Empowering Mathematical Reasoning for Large Language Models via Tool-Augmented Agent
23. ICLR 2026Algorithm Generation via Creative Ideation
24. ICLR 2026Aligning Deep Implicit Preferences by Learning to Reason Defensively
25. ICLR 2026Alignment-Weighted DPO: A principled reasoning approach to improve alignment
26. ICLR 2026All Code, No Thought: Language Models Struggle to Reason in Ciphered Language
27. ICLR 2026ALM-MTA: Front-Door Causal Multi-Touch Attribution Method for Creator-Ecosystem Optimization
28. ICLR 2026AlphaAgentEvo: Evolution-Oriented Alpha Mining via Self-Evolving Agentic Reinforcement Learning
29. ICLR 2026AlphaAlign: Incentivizing Safety Alignment with Extremely Simplified Reinforcement Learning
30. ICLR 2026Analytica: Soft Propositional Reasoning for Robust and Scalable LLM-Driven Analysis
31. ICLR 2026Architecture-Agnostic Test-Time Adaptation via Backprop-Free Embedding Alignment
32. ICLR 2026Are Reasoning LLMs Robust to Interventions on their Chain-of-Thought?
33. ICLR 2026ARES: Multimodal Adaptive Reasoning via Difficulty-Aware Token-Level Entropy Shaping
34. ICLR 2026ARMOR: Aligning Secure and Safe Large Language Models via Meticulous Reasoning
35. ICLR 2026Asymmetric Proximal Policy Optimization: mini-critics boost LLM reasoning
36. ICLR 2026Attention as a Compass: Efficient Exploration for Process-Supervised RL in Reasoning Models
37. ICLR 2026ATTS: Asynchronous Test-Time Scaling via Conformal Prediction
38. ICLR 2026AUHead: Realistic Emotional Talking Head Generation via Action Units Control
39. ICLR 2026AutoDrive-R²: Incentivizing Reasoning and Self-Reflection Capacity for VLA Model in Autonomous Driving
40. ICLR 2026AutoGPS: Automated Geometry Problem Solving via Multimodal Formalization and Deductive Reasoning
41. ICLR 2026AVERE: Improving Audiovisual Emotion Reasoning with Preference Optimization
42. ICLR 2026BARREL: Boundary-Aware Reasoning for Factual and Reliable LRMs
43. ICLR 2026Bee: A High-Quality Corpus and Full-Stack Suite to Unlock Advanced Fully Open MLLMs
44. ICLR 2026Benefits and Limitations of Communication in Multi-Agent Reasoning
45. ICLR 2026Best-of-Infinity: Asymptotic Performance of Test-Time Compute
46. ICLR 2026Beyond Binary Rewards: Training LMs to Reason About Their Uncertainty
47. ICLR 2026Beyond Classification Accuracy: Neural-MedBench and the Need for Deeper Reasoning Benchmarks
48. ICLR 2026Beyond English-Centric Training: How Reinforcement Learning Improves Cross-Lingual Reasoning in LLMs
49. ICLR 2026Beyond Pass@ 1: Self-Play with Variational Problem Synthesis Sustains RLVR
50. ICLR 2026Beyond Speedup - Utilizing KV Cache for Sampling and Reasoning

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。