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 577 篇，第 9 / 12 页

  1. NeurIPS 2026Can LLM Agents Respond to Disasters? Benchmarking Heterogeneous Geospatial Reasoning in Emergency Operations
  2. NeurIPS 2026CasePlay: Self-Play Reinforcement Learning from Case Reports for Medical Reasoning
  3. NeurIPS 2026CAVE: A Structured Credit Assignment Approach for Fragmented Visual Evidence Reasoning
  4. NeurIPS 2026CellularS2-Bench: A Staged, Evidence-Grounded Benchmark for Cellular Network Security Reasoning
  5. NeurIPS 2026ChainSpace: A Chained-Reasoning Paradigm for Spatial Intelligence
  6. NeurIPS 2026CineMME: Benchmarking Fine-Grained Perception and Plot Reasoning in Multimodal Large Language Models
  7. NeurIPS 2026CircuitSeer: Mining High-Quality Data by Probing Mathematical Reasoning Circuits in LLMs
  8. NeurIPS 2026Collaborative Reasoning Distillation via Cross-Feedback and Coherent Curation
  9. NeurIPS 2026Commit Then Explore: Reasoning Models Diversify, Not Converge
  10. NeurIPS 2026Compositional Generalization Certificates via the Van Kampen Theorem
  11. NeurIPS 2026Concise Reasoning Through the Lens of Lagrangian Optimization
  12. NeurIPS 2026Confidence-Calibrated Inference Expansion for Evaluator-Guided Test-Time Reasoning
  13. NeurIPS 2026Consolidating Reasoning with Test-Time Learning
  14. NeurIPS 2026Contractive Restoring Flows: Robust Reasoning Distillation via Orbital Stability
  15. NeurIPS 2026Contrastive Thinking Decoding: Steering Answer Generation in Reasoning Models
  16. NeurIPS 2026Convex Compositional Reasoning Models
  17. NeurIPS 2026CoRE-RL: Co-evolving Reasoning Trajectories and Evidence Subgraphs with Learned Evidence Projection
  18. NeurIPS 2026Correct but Unselectable: The Hidden Interface Tax in Multi-Candidate Reasoning
  19. NeurIPS 2026Corrective Diffusion Language Models
  20. NeurIPS 2026Credit Assignment with Resets in Language Model Reasoning
  21. NeurIPS 2026CryptanalysisBench: Can LLMs do cryptanalysis?
  22. NeurIPS 2026CurveBench: A Benchmark for Exact Topological Reasoning over Nested Jordan Curves
  23. NeurIPS 2026DACE RL for Compute Efficient Reinforcement Learning in Small Model Reasoning
  24. NeurIPS 2026Data Diversity Drives the Emergence of Symbolic Mechanisms Supporting Abstract Reasoning
  25. NeurIPS 2026Decoding the Critique Mechanism in Large Reasoning Models
  26. NeurIPS 2026Deep Reasoning in General Purpose Agents via Structured Meta-Cognition
  27. NeurIPS 2026Depth-Recurrent Attention Mixtures: Giving Latent Reasoning the Attention it Deserves
  28. NeurIPS 2026DocScope: Benchmarking Verifiable Reasoning for Trustworthy Long-Document Understanding
  29. NeurIPS 2026Does Your Large Language Model Have An Intuitive Sense of The Difficulty of A Question?
  30. NeurIPS 2026DRAGON : A Benchmark for Evidence-Grounded Visual Reasoning over Diagrams
  31. NeurIPS 2026DualSAT: A Dual-Branch GNN-Transformer Framework for SAT Solving
  32. NeurIPS 2026Efficient Reasoning via Constrained Optimization in Latent Space
  33. NeurIPS 2026Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Models
  34. NeurIPS 2026Exact Posterior Score Estimation for Solving Linear Inverse Problems
  35. NeurIPS 2026Extraneous Cognitive Load in Large Language Models
  36. NeurIPS 2026FACBench: A Benchmark for Formal-Anchor Collisions in Multilingual Mathematical Grounding
  37. NeurIPS 2026Failure Profiling and Reachable Trajectory Selection for Reasoning Distillation
  38. NeurIPS 2026FaithSieve: Fine-Grained Evaluation of Math Proofs with Faithful Formal Evidence
  39. NeurIPS 2026Fixed-Point Reasoning: Stable and Adaptive Deep Looped Models
  40. NeurIPS 2026From Finding to Linking: Benchmarking and Advancing Cross-Long-Video Reasoning for Multimodal LLMs
  41. NeurIPS 2026From Reasoning Chains to Verifiable Subproblems: Curriculum Reinforcement Learning Enables Credit Assignment for LLM Reasoning
  42. NeurIPS 2026From Solver Trajectories to Teaching Trajectories: Cognition-Aligned Reasoning Distillation
  43. NeurIPS 2026GeLVR: Geometry-Consistent Latent Visual Reasoning in Multimodal LLMs
  44. NeurIPS 2026GeoDial: A Multimodal Dialog Tutoring Dataset for Geometry Problem-Solving with Visual Tutor Turns
  45. NeurIPS 2026Geometric Latent Reasoning Induces Shorter Generations in LLMs
  46. NeurIPS 2026Geometric Signatures of Reasoning: A Spectral Perspective on Task Hardness
  47. NeurIPS 2026GeoX: Mastering Geospatial Reasoning Through Self-Play and Verifiable Rewards
  48. NeurIPS 2026GUI-Libra: Data-Efficient Post-Training for Reliable Reasoning-and-Acting in Native GUI Agents
  49. NeurIPS 2026Hide to See: Reasoning-prefix Masking for Visual-anchored Thinking in VLM Distillation
  50. NeurIPS 2026HierRR: Enhancing Instruction Alignment in Open-Vocabulary Indoor Scene Synthesis via Agentic Hierarchical Reasoning and Reflection

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