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 8 / 26 页

  1. NeurIPS 2026Watching Itself Watch: Self-Auditing Visual Reliance for Video Reasoning
  2. NeurIPS 2026Weisfeiler and Leman Follow the Arrow of Time: Expressive Power of Message Passing in Temporal Event Graphs
  3. NeurIPS 2026What MLLMs Learn about When they Learn about Multimodal Reasoning
  4. NeurIPS 2026What should post-training optimize? A test-time scaling law perspective
  5. NeurIPS 2026What’s Holding Back Latent Visual Reasoning?
  6. NeurIPS 2026When LLMs Know but Fail to Reason: Injecting Memory for Reasoning Enhancement
  7. NeurIPS 2026When Reasoning Meets Its Laws
  8. NeurIPS 2026Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression
  9. NeurIPS 2026Why Transformer-Based Language Models Need Explicit Mechanisms of Cognitive Control
  10. NeurIPS 2026Why Transformers Struggle with Distribution-Independent In-Context Learning
  11. NeurIPS 2026Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor’s Internal States
  12. NeurIPS 2025$\texttt{G1}$: Teaching LLMs to Reason on Graphs with Reinforcement Learning
  13. NeurIPS 2025$Q\sharp$: Provably Optimal Distributional RL for LLM Post-Training
  14. NeurIPS 2025A Closer Look at TabPFN v2: Understanding Its Strengths and Extending Its Capabilities
  15. NeurIPS 2025A Difference-of-Convex Functions Approach to Energy-Based Iterative Reasoning
  16. 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
  17. NeurIPS 2025A learnability analysis on neuro-symbolic learning
  18. NeurIPS 2025A Little Depth Goes a Long Way: The Expressive Power of Log-Depth Transformers
  19. NeurIPS 2025A Theoretical Study on Bridging Internal Probability and Self-Consistency for LLM Reasoning
  20. NeurIPS 2025A Unified Reasoning Framework for Holistic Zero-Shot Video Anomaly Analysis
  21. NeurIPS 2025A*-Thought: Efficient Reasoning via Bidirectional Compression for Low-Resource Settings
  22. NeurIPS 2025A2Seek: Towards Reasoning-Centric Benchmark for Aerial Anomaly Understanding
  23. NeurIPS 2025Absolute Zero: Reinforced Self-play Reasoning with Zero Data
  24. NeurIPS 2025AbstentionBench: Reasoning LLMs Fail on Unanswerable Questions
  25. NeurIPS 2025Accelerated Sampling from Masked Diffusion Models via Entropy Bounded Unmasking
  26. NeurIPS 2025Accelerating RL for LLM Reasoning with Optimal Advantage Regression
  27. NeurIPS 2025AceReason-Nemotron: Advancing Math and Code Reasoning through Reinforcement Learning
  28. NeurIPS 2025Actial: Activate Spatial Reasoning Ability of Multimodal Large Language Models
  29. NeurIPS 2025Activation Control for Efficiently Eliciting Long Chain-of-thought Ability of Language Models
  30. NeurIPS 2025Activation-Guided Consensus Merging for Large Language Models
  31. NeurIPS 2025Ada-R1: Hybrid-CoT via Bi-Level Adaptive Reasoning Optimization
  32. NeurIPS 2025Adaptive Divergence Regularized Policy Optimization for Fine-tuning Generative Models
  33. NeurIPS 2025AdaReasoner: Adaptive Reasoning Enables More Flexible Thinking
  34. NeurIPS 2025AdaSTaR: Adaptive Data Sampling for Training Self-Taught Reasoners
  35. NeurIPS 2025AffordBot: 3D Fine-grained Embodied Reasoning via Multimodal Large Language Models
  36. NeurIPS 2025AgentAuditor: Human-level Safety and Security Evaluation for LLM Agents
  37. NeurIPS 2025AgentTTS: Large Language Model Agent for Test-time Compute-optimal Scaling Strategy in Complex Tasks
  38. NeurIPS 2025Analog Foundation Models
  39. NeurIPS 2025Analyzing the Power of Chain of Thought through Memorization Capabilities
  40. NeurIPS 2025Anchored Diffusion Language Model
  41. NeurIPS 2025AnomalyCoT: A Multi-Scenario Chain-of-Thought Dataset for Multimodal Large Language Models
  42. NeurIPS 2025Any Large Language Model Can Be a Reliable Judge: Debiasing with a Reasoning-based Bias Detector
  43. NeurIPS 2025APOLLO: Automated LLM and Lean Collaboration for Advanced Formal Reasoning
  44. NeurIPS 2025Are Language Models Efficient Reasoners? A Perspective from Logic Programming
  45. NeurIPS 2025Are Large Reasoning Models Good Translation Evaluators? Analysis and Performance Boost
  46. NeurIPS 2025ARM: Adaptive Reasoning Model
  47. NeurIPS 2025AtmosSci-Bench: Evaluating the Recent Advance of Large Language Model for Atmospheric Science
  48. NeurIPS 2025Atom of Thoughts for Markov LLM Test-Time Scaling
  49. NeurIPS 2025Atomic Thinking of LLMs: Decoupling and Exploring Mathematical Reasoning Abilities
  50. NeurIPS 2025Attention (as Discrete-Time Markov) Chains

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