数学推理论文趋势 2023–2026

定理与解题

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 1,085 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

数学推理论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20231917111057
202452343912137
2025190614518314
202620817511381577

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

全部数学推理论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 1,085 篇，第 12 / 22 页

  1. NeurIPS 2026Test-Time Learning with an Evolving Library
  2. NeurIPS 2026The Capability Frontier of GRPO
  3. NeurIPS 2026The Era of Agentic Organization: Learning to Organize with Language Models
  4. NeurIPS 2026The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models
  5. NeurIPS 2026They Can See It but not Say It: Iterative Self Knowledge Re-expression in Visual Reasoning Relative Pose Identification
  6. NeurIPS 2026TIGER: Bridging the Multimodal Reasoning-Access Gap via Modality Counterfactuals
  7. NeurIPS 2026Time to Pay Attention! Understanding High Complexity Corpus Reasoning Tasks
  8. NeurIPS 2026Train at the Moving Edge: Rollout-Efficient RL for Large Reasoning Models
  9. NeurIPS 2026Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
  10. NeurIPS 2026Training-Free Dynamic Upcycling of Expert Language Models
  11. NeurIPS 2026Treat Bias as Noise: Training Bias-Robust LLM Reasoning via Reinforcement Learning
  12. NeurIPS 2026Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA
  13. NeurIPS 2026TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning
  14. NeurIPS 2026Understanding the Out-of-Distribution Generalization of Chain-of-Thought Reasoning in LLMs
  15. NeurIPS 2026Unifying Reasoning and Planning through Energy Minimization
  16. NeurIPS 2026UniRAP: Towards Unified Part-level Physical Affordance Reasoning and Actionable Perception
  17. NeurIPS 2026Value-Aware Stochastic KV Cache Eviction for Reasoning Models
  18. NeurIPS 2026Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization
  19. NeurIPS 2026Verifier-Backed Hard Problem Generation for Mathematical Reasoning
  20. NeurIPS 2026VeriWorld: A Verifiable Visual SWE-Bench for Spatial Reasoning in 3D Environments
  21. NeurIPS 2026VI-CuRL: Stabilizing Verifier-Independent RL Reasoning via Confidence-Guided Variance Reduction
  22. NeurIPS 2026VISD: Enhancing Video Reasoning via Structured Self-Distillation
  23. NeurIPS 2026What’s Holding Back Latent Visual Reasoning?
  24. NeurIPS 2026When Further Realization Is Unnecessary: Amortized Reasoning for Long-Horizon LLM Agents
  25. NeurIPS 2026When LLMs Know but Fail to Reason: Injecting Memory for Reasoning Enhancement
  26. NeurIPS 2026Where to Approximate in Neurosymbolic Inference?
  27. NeurIPS 2026Why Struggle with Continuous Latents? Interpretable Discrete Latent Reasoning via Rendered Compression
  28. CVPR 20253D-Mem: 3D Scene Memory for Embodied Exploration and Reasoning
  29. CVPR 2025Black Swan: Abductive and Defeasible Video Reasoning in Unpredictable Events
  30. CVPR 2025Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence
  31. CVPR 2025Coarse Correspondences Boost Spatial-Temporal Reasoning in Multimodal Language Model
  32. CVPR 2025Explainable Saliency: Articulating Reasoning with Contextual Prioritization
  33. CVPR 2025FirePlace: Geometric Refinements of LLM Common Sense Reasoning for 3D Object Placement
  34. CVPR 2025Gromov-Wasserstein Problem with Cyclic Symmetry
  35. CVPR 2025Improving Diffusion Inverse Problem Solving with Decoupled Noise Annealing
  36. CVPR 2025MV-MATH: Evaluating Multimodal Math Reasoning in Multi-Visual Contexts
  37. CVPR 2025Perception Tokens Enhance Visual Reasoning in Multimodal Language Models
  38. CVPR 2025PRaDA: Projective Radial Distortion Averaging
  39. CVPR 2025Reasoning to Attend: Try to Understand How <SEG> Token Works
  40. CVPR 2025Reconstructing Close Human Interaction with Appearance and Proxemics Reasoning
  41. CVPR 2025SeqAfford: Sequential 3D Affordance Reasoning via Multimodal Large Language Model
  42. CVPR 2025Spatial457: A Diagnostic Benchmark for 6D Spatial Reasoning of Large Mutimodal Models
  43. CVPR 2025TSP-Mamba: The Travelling Salesman Problem Meets Mamba for Image Super-resolution and Beyond
  44. CVPR 2025VISCO: Benchmarking Fine-Grained Critique and Correction Towards Self-Improvement in Visual Reasoning
  45. CVPR 2025Visual Agentic AI for Spatial Reasoning with a Dynamic API
  46. ICLR 2025Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages
  47. ICLR 2025Arithmetic Without Algorithms: Language Models Solve Math with a Bag of Heuristics
  48. ICLR 2025B-STaR: Monitoring and Balancing Exploration and Exploitation in Self-Taught Reasoners
  49. ICLR 2025Can LLMs Solve Longer Math Word Problems Better?
  50. ICLR 2025CogCoM: A Visual Language Model with Chain-of-Manipulations Reasoning

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 查数学推理在 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": "math-reasoning"}

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数学推理论文？
共 1,085 篇，按年份分别是 2023 年 57 篇、2024 年 137 篇、2025 年 314 篇、2026 年 577 篇。
NeurIPS 2026 有多少篇数学推理论文？
NeurIPS 2026 有 208 篇数学推理论文，上一届是 190 篇。
ICLR 2026 有多少篇数学推理论文？
ICLR 2026 有 175 篇数学推理论文，上一届是 61 篇。
ICML 2026 有多少篇数学推理论文？
ICML 2026 有 113 篇数学推理论文，上一届是 45 篇。
CVPR 2026 有多少篇数学推理论文？
CVPR 2026 有 81 篇数学推理论文，上一届是 18 篇。
哪个会议的数学推理论文最多？
NeurIPS，2023–2026 年共 469 篇。

「神经符号」下的其他主题