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 10 / 22 页

  1. NeurIPS 2026How do Small Transformer Models Learn Hard Math Tasks?
  2. NeurIPS 2026How does RL Post-training Induce Skill Composition? A Case Study on Countdown
  3. NeurIPS 2026Identified-Set Geometry of Distributional Model Extraction under Top-K Censored API Access
  4. NeurIPS 2026INFUSER: Influence-Guided Self-Evolution Improves Reasoning
  5. NeurIPS 2026Interactive Combinatorial Reinforcement Learning for Knowledge Graph Reasoning
  6. NeurIPS 2026Iterative Nonlinear Computation Underlying Abstract Reasoning
  7. NeurIPS 2026Language Models Need Sleep
  8. NeurIPS 2026Latent Spatial Reasoning: Building Innate 3D Awareness via Latent-Space Distillation
  9. NeurIPS 2026LatentUM: Unleashing the Potential of Interleaved Cross-Modal Reasoning via a Latent-Space Unified Model
  10. NeurIPS 2026LeAct: Learning to Reason from Expert Actions
  11. NeurIPS 2026LEAD: Length-Efficient Adaptive and Dynamic Reasoning for Large Language Models
  12. NeurIPS 2026Learning to Complete Extremal Mathematical Structures
  13. NeurIPS 2026Learning When to Think: Dual-Reference Offline Optimization for Adaptive VLM Reasoning
  14. NeurIPS 2026LLM Agents Already Know When to Call Tools - Even Without Reasoning
  15. NeurIPS 2026LLMs Show No Signs Of Individuated Metacognition
  16. NeurIPS 2026Look Before You Reason: Implicit Visual Thinking for Efficient Multimodal Reasoning
  17. NeurIPS 2026Low-Rank Hierarchical Merging for Efficient Long-to-Short Reasoning
  18. NeurIPS 2026MammoGPS: A Benchmark for Visual Grounding, Perception, and Spatial Reasoning in Mammography
  19. NeurIPS 2026Masked Diffusion Language Agents for Tool-Integrated Chemical Reasoning
  20. NeurIPS 2026MCPHallu: Benchmarking Reasoning, Execution, and Memory Hallucinations in MCP Agents
  21. NeurIPS 2026Measuring Weak-to-Strong Legibility of Reasoning Models
  22. NeurIPS 2026MedZERO: Self-Evolving Agents for Open-Ended Medical Reasoning Through Controlled Knowledge Accumulation
  23. NeurIPS 2026MemPilot: Learning Transferable Latent Memory Mechanisms for LLM Reasoning
  24. NeurIPS 2026Mental Imagery That Matters: Curing Latent Collapse in Multimodal Reasoning
  25. NeurIPS 2026MindLoom: Composing Thought Modes for Frontier-Level Reasoning Data Synthesis
  26. NeurIPS 2026MinPath: Learning Efficient LLM Reasoning via Minimal Dependency Paths
  27. NeurIPS 2026MIRA: Reinforcing Multimodal Reasoning via Deceptive Contextual Augmentation
  28. NeurIPS 2026MIRAGE: Mobile Agents with Implicit Reasoning and Generative World Models
  29. NeurIPS 2026Mitigating Factual Hallucination in Large Reasoning Models via Mixed-Mode Advantage Regularization
  30. NeurIPS 2026Mitigating Overthinking in Large Reasoning Language Models via Reasoning Path Deviation Monitoring
  31. NeurIPS 2026MMFineReason: Closing the Multimodal Reasoning Gap via Open Data-Centric Methods
  32. NeurIPS 2026MotionHalluc: Diagnosing Kinematic Hallucinations in Fine-Grained Motion Reasoning
  33. NeurIPS 2026MUX: Continuous Reasoning via Multiplexed Tokens
  34. NeurIPS 2026Natural Synthesis: Outperforming Reactive Synthesis Tools with Large Reasoning Models
  35. NeurIPS 2026On the Token Value Inequality in Efficient Reasoning
  36. NeurIPS 2026OS-Pruner: Pruning Chains-of-Thought of Reasoning Models via Optimal Stopping
  37. NeurIPS 2026Outcome-Based RL Provably Leads Transformers to Reason, but Only With the Right Data
  38. NeurIPS 2026PAC Reasoning: Controlling the Performance Loss for Efficient Reasoning
  39. NeurIPS 2026Pause and Reflect: Conformal Aggregation for Chain-of-Thought Reasoning
  40. NeurIPS 2026Perceive, Interact, Reason: Building Tool-Augmented Visual Agents for Spatial Reasoning
  41. NeurIPS 2026PhysGraphNet: Physical-State Scene Graphs via Latent Graph Reasoning and Counterfactual Supervision
  42. NeurIPS 2026PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop
  43. NeurIPS 2026Plausibility Is Not Prediction: Contrastive Evidence for LLM-Based Cellular Perturbation Reasoning
  44. NeurIPS 2026Position: Robust Reasoning Requires Internal Time, Not Scale Alone
  45. NeurIPS 2026Precise but Uncoupled: Reviewer Precision Does Not Guarantee Critique Uptake in Multi-Agent Math Reasoning
  46. NeurIPS 2026Preserving Exploration for LLM Reasoning via Mean Order-Statistic Alignment
  47. NeurIPS 2026Probabilistic Recursive Reasoning
  48. NeurIPS 2026Probing the Trajectories of Reasoning Traces in Large Language Models
  49. NeurIPS 2026Problem-Dependent Dynamic Regret over a Predictor Class with One-Gradient Feedback
  50. NeurIPS 2026Programmatic Reasoning with Structural Schema: A Unified Framework for Multi-Table Inference

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