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 469 篇，第 4 / 10 页

  1. NeurIPS 2026Scaling Causal Reasoning with Increasingly Complex Causal Simulators
  2. NeurIPS 2026Seeing or Rationalizing? Scene-Evidence-Guided Chain-of-Thought for Faithful 3D Multimodal Reasoning
  3. NeurIPS 2026Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning
  4. NeurIPS 2026Self-Compacting Language Model Agents
  5. NeurIPS 2026Semantic Search over 9 Million Mathematical Theorems
  6. NeurIPS 2026SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
  7. NeurIPS 2026SH$^2$: A Mathematician-Curated benchmark for Assessing Research-level Math Capabilities of LLMs
  8. NeurIPS 2026Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
  9. NeurIPS 2026Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots
  10. NeurIPS 2026SoDeArena: A Socially-Situated Reasoning Benchmark for Large Language Models
  11. NeurIPS 2026Solving Every Step Is Not Enough: Milestone Oracles Reveal a Composition Gap in LLM Math Reasoning
  12. NeurIPS 2026Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache
  13. NeurIPS 2026Sparse Expansion Utility: Identifying and Routing to Pivotal Steps in LLM Reasoning Chains
  14. NeurIPS 2026SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera
  15. NeurIPS 2026Stability in Multi-Step Reasoning via Jacobian-based Error Accumulation Analysis
  16. NeurIPS 2026Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
  17. NeurIPS 2026STAR-Math: Multi-Agent Mathematical Reasoning under Persistent Meta-Strategic Supervision
  18. NeurIPS 2026State of Thought Enables Endogenous Reasoning
  19. NeurIPS 2026StateTree: Enhancing Long-term Dialogue Reasoning via Reinforcement Learning
  20. NeurIPS 2026Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces
  21. NeurIPS 2026Step-wise Rubric Rewards for LLM Reasoning
  22. NeurIPS 2026Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
  23. NeurIPS 2026Stop or Restart? Principled Inference Control for Large Reasoning Models via the Pandora's Box
  24. NeurIPS 2026Strategist: Designing Agentic Reasoning at Scale
  25. NeurIPS 2026STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning
  26. NeurIPS 2026Structural Rationale Distillation via Reasoning Space Compression
  27. NeurIPS 2026TargetSage: Identifying Therapeutic Target Genes with Interpretable and Robust LLM Reasoning
  28. NeurIPS 2026TARP: Trace-Anchored Regularization Prior for Retaining Stepwise Reasoning
  29. NeurIPS 2026TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
  30. NeurIPS 2026Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher
  31. NeurIPS 2026TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought Reasoning
  32. NeurIPS 2026Test-Time Learning with an Evolving Library
  33. NeurIPS 2026The Capability Frontier of GRPO
  34. NeurIPS 2026The Era of Agentic Organization: Learning to Organize with Language Models
  35. NeurIPS 2026The Reasoning Boundary Paradox: How Reinforcement Learning Constrains Language Models
  36. NeurIPS 2026They Can See It but not Say It: Iterative Self Knowledge Re-expression in Visual Reasoning Relative Pose Identification
  37. NeurIPS 2026TIGER: Bridging the Multimodal Reasoning-Access Gap via Modality Counterfactuals
  38. NeurIPS 2026Time to Pay Attention! Understanding High Complexity Corpus Reasoning Tasks
  39. NeurIPS 2026Train at the Moving Edge: Rollout-Efficient RL for Large Reasoning Models
  40. NeurIPS 2026Training with Harnesses: On-Policy Harness Self-Distillation for Complex Reasoning
  41. NeurIPS 2026Training-Free Dynamic Upcycling of Expert Language Models
  42. NeurIPS 2026Treat Bias as Noise: Training Bias-Robust LLM Reasoning via Reinforcement Learning
  43. NeurIPS 2026Triggering Generalist Reasoning via Predictive Uncertainty for Dual-System VLA
  44. NeurIPS 2026TSQAgent: Rating Time Series Data Quality via Dedicated Agentic Reasoning
  45. NeurIPS 2026Understanding the Out-of-Distribution Generalization of Chain-of-Thought Reasoning in LLMs
  46. NeurIPS 2026Unifying Reasoning and Planning through Energy Minimization
  47. NeurIPS 2026UniRAP: Towards Unified Part-level Physical Affordance Reasoning and Actionable Perception
  48. NeurIPS 2026Value-Aware Stochastic KV Cache Eviction for Reasoning Models
  49. NeurIPS 2026Verifiable Environments Are LEGO Bricks: Recursive Composition for Reasoning Generalization
  50. NeurIPS 2026Verifier-Backed Hard Problem Generation for Mathematical 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