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 500 篇，第 9 / 10 页

  1. NeurIPS 2025Sparse Diffusion Autoencoder for Test-time Adapting Prediction of Complex Systems
  2. NeurIPS 2025SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning
  3. NeurIPS 2025SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning
  4. NeurIPS 2025SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
  5. NeurIPS 2025SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models
  6. NeurIPS 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning
  7. NeurIPS 2025SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning
  8. NeurIPS 2025Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
  9. NeurIPS 2025StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs
  10. NeurIPS 2025STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization
  11. NeurIPS 2025Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs
  12. NeurIPS 2025Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
  13. NeurIPS 2025SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
  14. NeurIPS 2025SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications
  15. NeurIPS 2025SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning
  16. NeurIPS 2025SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
  17. NeurIPS 2025System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts
  18. NeurIPS 2025T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
  19. NeurIPS 2025Table as a Modality for Large Language Models
  20. NeurIPS 2025TCM-Ladder: A Benchmark for Multimodal Question Answering on Traditional Chinese Medicine
  21. NeurIPS 2025Teaching Language Models to Reason with Tools
  22. NeurIPS 2025TempSamp-R1: Effective Temporal Sampling with Reinforcement Fine-Tuning for Video LLMs
  23. NeurIPS 2025Test-Time Adaptation by Causal Trimming
  24. NeurIPS 2025The Dual Nature of Plasticity Loss in Deep Continual Learning: Dissection and Mitigation
  25. NeurIPS 2025The Emergence of Abstract Thought in Large Language Models Beyond Any Language
  26. NeurIPS 2025The First Few Tokens Are All You Need: An Efficient and Effective Unsupervised Prefix Fine-Tuning Method for Reasoning Models
  27. NeurIPS 2025The Hawthorne Effect in Reasoning Models: Evaluating and Steering Test Awareness
  28. NeurIPS 2025The Illusion of Thinking: Understanding the Strengths and Limitations of Reasoning Models via the Lens of Problem Complexity
  29. NeurIPS 2025The Overthinker's DIET: Cutting Token Calories with DIfficulty-AwarE Training
  30. NeurIPS 2025The Promise of RL for Autoregressive Image Editing
  31. NeurIPS 2025The Surprising Effectiveness of Negative Reinforcement in LLM Reasoning
  32. NeurIPS 2025Think Only When You Need with Large Hybrid-Reasoning Models
  33. NeurIPS 2025Think or Not? Exploring Thinking Efficiency in Large Reasoning Models via an Information-Theoretic Lens
  34. NeurIPS 2025Think Silently, Think Fast: Dynamic Latent Compression of LLM Reasoning Chains
  35. NeurIPS 2025Think-RM: Enabling Long-Horizon Reasoning in Generative Reward Models
  36. NeurIPS 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent Planning
  37. NeurIPS 2025ThinkBench: Dynamic Out-of-Distribution Evaluation for Robust LLM Reasoning
  38. NeurIPS 2025Thinker: Learning to Think Fast and Slow
  39. NeurIPS 2025Thinking in Character: Advancing Role-Playing Agents with Role-Aware Reasoning
  40. NeurIPS 2025Thinking vs. Doing: Improving Agent Reasoning by Scaling Test-Time Interaction
  41. NeurIPS 2025Thinkless: LLM Learns When to Think
  42. NeurIPS 2025ThinkSound: Chain-of-Thought Reasoning in Multimodal LLMs for Audio Generation and Editing
  43. NeurIPS 2025Thoughts Are All Over the Place: On the Underthinking of Long Reasoning Models
  44. NeurIPS 2025TimE: A Multi-level Benchmark for Temporal Reasoning of LLMs in Real-World Scenarios
  45. NeurIPS 2025Titans: Learning to Memorize at Test Time
  46. NeurIPS 2025TokenSqueeze: Performance-Preserving Compression for Reasoning LLMs
  47. NeurIPS 2025TOMCAT: Test-time Comprehensive Knowledge Accumulation for Compositional Zero-Shot Learning
  48. NeurIPS 2025Too Late to Recall: Explaining the Two-Hop Problem in Multimodal Knowledge Retrieval
  49. NeurIPS 2025Tool-Augmented Spatiotemporal Reasoning for Streamlining Video Question Answering Task
  50. NeurIPS 2025Topology of Reasoning: Understanding Large Reasoning Models through Reasoning Graph Properties

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