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

每年论文数

各会议论文数

按年份和会议统计

推理模型论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20232715710933470
2024121846343311
202550020315970932
20263616525822041,799

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

全部推理模型论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,253 篇，第 10 / 26 页

  1. NeurIPS 2025Collaborative Reasoner: Self-Improving Social Agents with Synthetic Conversations
  2. NeurIPS 2025Composing Global Solutions to Reasoning Tasks via Algebraic Objects in Neural Nets
  3. NeurIPS 2025Compositional Neural Network Verification via Assume-Guarantee Reasoning
  4. NeurIPS 2025Compositional Reasoning with Transformers, RNNs, and Chain of Thought
  5. NeurIPS 2025Conformal Information Pursuit for Interactively Guiding Large Language Models
  6. NeurIPS 2025Contextual Integrity in LLMs via Reasoning and Reinforcement Learning
  7. NeurIPS 2025Continuous Thought Machines
  8. NeurIPS 2025Contrastive Representations for Temporal Reasoning
  9. NeurIPS 2025Controlling Thinking Speed in Reasoning Models
  10. NeurIPS 2025CoRe: Benchmarking LLMs’ Code Reasoning Capabilities through Static Analysis Tasks
  11. NeurIPS 2025CoT Information: Improved Sample Complexity under Chain-of-Thought Supervision
  12. NeurIPS 2025CoT Red-Handed: Stress Testing Chain-of-Thought Monitoring
  13. NeurIPS 2025Counterfactual Reasoning for Steerable Pluralistic Value Alignment of Large Language Models
  14. NeurIPS 2025Counterfactual reasoning: an analysis of in-context emergence
  15. NeurIPS 2025CPPO: Accelerating the Training of Group Relative Policy Optimization-Based Reasoning Models
  16. NeurIPS 2025Creativity or Brute Force? Using Brainteasers as a Window into the Problem-Solving Abilities of Large Language Models
  17. NeurIPS 2025CReFT-CAD: Boosting Orthographic Projection Reasoning for CAD via Reinforcement Fine-Tuning
  18. NeurIPS 2025Curriculum Abductive Learning
  19. NeurIPS 2025Curriculum Design for Trajectory-Constrained Agent: Compressing Chain-of-Thought Tokens in LLMs
  20. NeurIPS 2025CURV: Coherent Uncertainty-Aware Reasoning in Vision-Language Models for X-Ray Report Generation
  21. NeurIPS 2025CXReasonBench: A Benchmark for Evaluating Structured Diagnostic Reasoning in Chest X-rays
  22. NeurIPS 2025d1: Scaling Reasoning in Diffusion Large Language Models via Reinforcement Learning
  23. NeurIPS 2025DAA: Amplifying Unknown Discrepancy for Test-Time Discovery
  24. NeurIPS 2025DAPO : Improving Multi-Step Reasoning Abilities of Large Language Models with Direct Advantage-Based Policy Optimization
  25. NeurIPS 2025DAPO: An Open-Source LLM Reinforcement Learning System at Scale
  26. NeurIPS 2025DeceptionBench: A Comprehensive Benchmark for AI Deception Behaviors in Real-world Scenarios
  27. NeurIPS 2025Delving into RL for Image Generation with CoT: A Study on DPO vs. GRPO
  28. NeurIPS 2025Demystifying Reasoning Dynamics with Mutual Information: Thinking Tokens are Information Peaks in LLM Reasoning
  29. NeurIPS 2025Dependency Matters: Enhancing LLM Reasoning with Explicit Knowledge Grounding
  30. NeurIPS 2025DIPO: Dual-State Images Controlled Articulated Object Generation Powered by Diverse Data
  31. NeurIPS 2025Direct Numerical Layout Generation for 3D Indoor Scene Synthesis via Spatial Reasoning
  32. NeurIPS 2025DisCO: Reinforcing Large Reasoning Models with Discriminative Constrained Optimization
  33. NeurIPS 2025Distilling LLM Agent into Small Models with Retrieval and Code Tools
  34. NeurIPS 2025DLoFT: Gradient-Decoupled Fine-Tuning for Generalizable Long Chain-of-Thought Reasoning
  35. NeurIPS 2025DMWM: Dual-Mind World Model with Long-Term Imagination
  36. NeurIPS 2025Do LVLMs Truly Understand Video Anomalies? Revealing Hallucination via Co-Occurrence Patterns
  37. NeurIPS 2025Does Reinforcement Learning Really Incentivize Reasoning Capacity in LLMs Beyond the Base Model?
  38. NeurIPS 2025Does Thinking More Always Help? Mirage of Test-Time Scaling in Reasoning Models
  39. NeurIPS 2025Don’t Think Longer, Think Wisely: Optimizing Thinking Dynamics for Large Reasoning Models
  40. NeurIPS 2025DreamPRM: Domain-reweighted Process Reward Model for Multimodal Reasoning
  41. NeurIPS 2025DrVD-Bench: Do Vision-Language Models Reason Like Human Doctors in Medical Image Diagnosis?
  42. NeurIPS 2025DSRF: A Dynamic and Scalable Reasoning Framework for Solving RPMs
  43. NeurIPS 2025DuetGraph: Coarse-to-Fine Knowledge Graph Reasoning with Dual-Pathway Global-Local Fusion
  44. NeurIPS 2025Dynamic Test-Time Compute Scaling in Control Policy: Difficulty-Aware Stochastic Interpolant Policy
  45. NeurIPS 2025EAGLE-3: Scaling up Inference Acceleration of Large Language Models via Training-Time Test
  46. NeurIPS 2025Efficiently Scaling LLM Reasoning Programs with Certaindex
  47. NeurIPS 2025EgoThinker: Unveiling Egocentric Reasoning with Spatio-Temporal CoT
  48. NeurIPS 2025Eliciting Reasoning in Language Models with Cognitive Tools
  49. NeurIPS 2025Emergent Risk Awareness in Rational Agents under Resource Constraints
  50. NeurIPS 2025Enhancing Compositional Reasoning in CLIP via Reconstruction and Alignment of Text Descriptions

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"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

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。

「前沿系统」下的其他主题