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 3,512 篇，第 53 / 71 页

  1. NeurIPS 2025Scaling Physical Reasoning with the PHYSICS Dataset
  2. NeurIPS 2025Scaling RL to Long Videos
  3. NeurIPS 2025Scaling Speculative Decoding with Lookahead Reasoning
  4. NeurIPS 2025Scaling up Test-Time Compute with Latent Reasoning: A Recurrent Depth Approach
  5. NeurIPS 2025SCAN: Self-Denoising Monte Carlo Annotation for Robust Process Reward Learning
  6. NeurIPS 2025Scent of Knowledge: Optimizing Search-Enhanced Reasoning with Information Foraging
  7. NeurIPS 2025SCOUT: Teaching Pre-trained Language Models to Enhance Reasoning via Flow Chain-of-Thought
  8. NeurIPS 2025scPilot: Large Language Model Reasoning Toward Automated Single-Cell Analysis and Discovery
  9. NeurIPS 2025SD-VLM: Spatial Measuring and Understanding with Depth-Encoded Vision-Language Models
  10. NeurIPS 2025SE-Agent: Self-Evolution Trajectory Optimization in Multi-Step Reasoning with LLM-Based Agents
  11. NeurIPS 2025Search and Refine During Think: Facilitating Knowledge Refinement for Improved Retrieval-Augmented Reasoning
  12. NeurIPS 2025Searching Latent Program Spaces
  13. NeurIPS 2025SeePhys: Does Seeing Help Thinking? – Benchmarking Vision-Based Physics Reasoning
  14. NeurIPS 2025Segment Policy Optimization: Effective Segment-Level Credit Assignment in RL for Large Language Models
  15. NeurIPS 2025Self-Verifying Reflection Helps Transformers with CoT Reasoning
  16. NeurIPS 2025SemCoT: Accelerating Chain-of-Thought Reasoning through Semantically-Aligned Implicit Tokens
  17. NeurIPS 2025Semi-off-Policy Reinforcement Learning for Vision-Language Slow-Thinking Reasoning
  18. NeurIPS 2025Sherlock: Self-Correcting Reasoning in Vision-Language Models
  19. NeurIPS 2025ShorterBetter: Guiding Reasoning Models to Find Optimal Inference Length for Efficient Reasoning
  20. NeurIPS 2025SIGMA: Refining Large Language Model Reasoning via Sibling-Guided Monte Carlo Augmentation
  21. NeurIPS 2025Simulating Society Requires Simulating Thought
  22. NeurIPS 2025Simulating Viva Voce Examinations to Evaluate Clinical Reasoning in Large Language Models
  23. NeurIPS 2025SiriuS: Self-improving Multi-agent Systems via Bootstrapped Reasoning
  24. NeurIPS 2025Sloth: scaling laws for LLM skills to predict multi-benchmark performance across families
  25. NeurIPS 2025SoFar: Language-Grounded Orientation Bridges Spatial Reasoning and Object Manipulation
  26. NeurIPS 2025Soft Thinking: Unlocking the Reasoning Potential of LLMs in Continuous Concept Space
  27. NeurIPS 2025SolidGeo: Measuring Multimodal Spatial Math Reasoning in Solid Geometry
  28. NeurIPS 2025SolverLLM: Leveraging Test-Time Scaling for Optimization Problem via LLM-Guided Search
  29. NeurIPS 2025Solving Inequality Proofs with Large Language Models
  30. NeurIPS 2025SoTA with Less: MCTS-Guided Sample Selection for Data-Efficient Visual Reasoning Self-Improvement
  31. NeurIPS 2025SPACE: SPike-Aware Consistency Enhancement for Test-Time Adaptation in Spiking Neural Networks
  32. NeurIPS 2025Sparse Diffusion Autoencoder for Test-time Adapting Prediction of Complex Systems
  33. NeurIPS 2025SpatialReasoner: Towards Explicit and Generalizable 3D Spatial Reasoning
  34. NeurIPS 2025SPC: Evolving Self-Play Critic via Adversarial Games for LLM Reasoning
  35. NeurIPS 2025SpecReason: Fast and Accurate Inference-Time Compute via Speculative Reasoning
  36. NeurIPS 2025SPRINT: Enabling Interleaved Planning and Parallelized Execution in Reasoning Models
  37. NeurIPS 2025SQL-R1: Training Natural Language to SQL Reasoning Model By Reinforcement Learning
  38. NeurIPS 2025SRPO: Enhancing Multimodal LLM Reasoning via Reflection-Aware Reinforcement Learning
  39. NeurIPS 2025Stop Summation: Min-Form Credit Assignment Is All Process Reward Model Needs for Reasoning
  40. NeurIPS 2025StreamBP: Memory-Efficient Exact Backpropagation for Long Sequence Training of LLMs
  41. NeurIPS 2025STRIDER: Navigation via Instruction-Aligned Structural Decision Space Optimization
  42. NeurIPS 2025Struct2D: A Perception-Guided Framework for Spatial Reasoning in MLLMs
  43. NeurIPS 2025Surprise3D: A Dataset for Spatial Understanding and Reasoning in Complex 3D Scenes
  44. NeurIPS 2025SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution
  45. NeurIPS 2025SWE-SQL: Illuminating LLM Pathways to Solve User SQL Issues in Real-World Applications
  46. NeurIPS 2025SwS: Self-aware Weakness-driven Problem Synthesis in Reinforcement Learning for LLM Reasoning
  47. NeurIPS 2025SynLogic: Synthesizing Verifiable Reasoning Data at Scale for Learning Logical Reasoning and Beyond
  48. NeurIPS 2025System-1.5 Reasoning: Traversal in Language and Latent Spaces with Dynamic Shortcuts
  49. NeurIPS 2025T2I-R1: Reinforcing Image Generation with Collaborative Semantic-level and Token-level CoT
  50. NeurIPS 2025Table as a Modality for Large Language Models

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