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
- 数学推理论文从 2023 年的 57 篇增长到 2026 年的 577 篇，三年间扩大到约 10 倍。
- NeurIPS 是发数学推理论文最多的会议，2023–2026 年共 469 篇，占四个会议总量的 43%。
- 交叉方向里涨得最快的是强化学习：同时属于两个主题的论文从 2023 年的 3 篇增至 2026 年的 140 篇。
- 在「神经符号」的 5 个主题里，它的 2026 年论文数排第 1；同组增长最快的可微推理是 2.5 倍，数学推理是 10 倍。
各会议论文数
按年份和会议统计
| 年份 | NeurIPS | ICLR | ICML | CVPR | 合计 |
|---|---|---|---|---|---|
| 2023 | 19 | 17 | 11 | 10 | 57 |
| 2024 | 52 | 34 | 39 | 12 | 137 |
| 2025 | 190 | 61 | 45 | 18 | 314 |
| 2026 | 208 | 175 | 113 | 81 | 577 |
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
- NeurIPS 2026A mathematical theory of balancing relational generalization and memorization
- ICML 2026ASyMOB: Algebraic Symbolic Mathematical Operations Benchmark
- ICLR 2026AutoGPS: Automated Geometry Problem Solving via Multimodal Formalization and Deductive Reasoning
- CVPR 2026Affine Perspective-Three-Point Problem
- NeurIPS 2025Are Language Models Efficient Reasoners? A Perspective from Logic Programming
- ICML 2025Autoformulation of Mathematical Optimization Models Using LLMs
- ICLR 2025Advancing Mathematical Reasoning in Language Models: The Impact of Problem-Solving Data, Data Synthesis Methods, and Training Stages
- CVPR 2025Bridging Viewpoint Gaps: Geometric Reasoning Boosts Semantic Correspondence
- NeurIPS 2024A Careful Examination of Large Language Model Performance on Grade School Arithmetic
- ICML 2024Accelerating Legacy Numerical Solvers by Non-intrusive Gradient-based Meta-solving
- ICLR 2024Don't Trust: Verify -- Grounding LLM Quantitative Reasoning with Autoformalization
- CVPR 2024E-GPS: Explainable Geometry Problem Solving via Top-Down Solver and Bottom-Up Generator
- NeurIPS 2023Evaluating and Improving Tool-Augmented Computation-Intensive Math Reasoning
- ICML 2023Automated Search for Conjectures on Mathematical Constants using Analysis of Integer Sequences
- ICLR 2023Differentiable Mathematical Programming for Object-Centric Representation Learning
- CVPR 2023Abstract Visual Reasoning: An Algebraic Approach for Solving Raven's Progressive Matrices
- NeurIPS 2026A Mechanistic Analysis of Looped Reasoning Language Models
- ICML 2026Beyond Theorem Proving: Formulation, Framework and Benchmark for Formal Problem-Solving
- ICLR 2026CogFlow: Bridging Perception and Reasoning through Knowledge Internalization for Visual Mathematical Problem Solving
- CVPR 2026Hilbert-Geo Solving Solid Geometric Problems by Neural-Symbolic Reasoning
全部数学推理论文
共 577 篇，第 11 / 12 页
- NeurIPS 2026Quantized Reasoning Models Think They Need to Think Longer, but They Do Not
- NeurIPS 2026Reasoning as Compression: Unifying Budget Forcing via the Conditional Information Bottleneck
- NeurIPS 2026Reasoning over Coupled Receptive Fields: Eliminating Subgraph Redundancy at Scale
- NeurIPS 2026Reasoning Pathologies in Large Language Models: A Diagnostic Perspective
- NeurIPS 2026Reasoning Warm-up: Scaling Label-free RL via Verifiable Surrogate Rewards
- NeurIPS 2026Reasoning with Undecoded Tokens in Diffusion Language Models
- NeurIPS 2026Reasoning-Aware IRT: Explainable Evaluation of Test-Time Scaling in Reasoning Models
- NeurIPS 2026Reasoning-based Spatial Prior (RSP): Learning Spatial Priors from Multimodal LLMs for Object Detection
- NeurIPS 2026Reasoning-Trace Collapse: Evaluating the Loss of Explicit Reasoning During Fine-Tuning
- NeurIPS 2026ReasoningShield: Safety Moderation over Reasoning Traces of Large Reasoning Models
- NeurIPS 2026Rebellious Student: Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR
- NeurIPS 2026Reinforcing Multimodal Reasoning Against Visual Degradation
- NeurIPS 2026Reject, Resample, Repeat: Understanding Parallel Reasoning in Language Model Inference
- NeurIPS 2026Reliable Chain-of-Thought via Prefix Consistency
- NeurIPS 2026RepoMirage: Probing Repository Context Reasoning in Code Agents with Perturbations
- NeurIPS 2026ReSET: Accurate Latency-Critical NVFP4 Reasoning via Step-Aware Temperature Scaling
- NeurIPS 2026RoboWits: Unexpected Challenges for Robotic Creative Problem Solving
- NeurIPS 2026s2n-bignum-bench: A practical benchmark for evaluating low-level code reasoning of LLMs
- NeurIPS 2026SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance
- NeurIPS 2026Scaling Causal Reasoning with Increasingly Complex Causal Simulators
- NeurIPS 2026Seeing or Rationalizing? Scene-Evidence-Guided Chain-of-Thought for Faithful 3D Multimodal Reasoning
- NeurIPS 2026Seirênes: Adversarial Self-Play with Evolving Distractions for LLM Reasoning
- NeurIPS 2026Self-Compacting Language Model Agents
- NeurIPS 2026Semantic Search over 9 Million Mathematical Theorems
- NeurIPS 2026SFT-then-RL Outperforms Mixed-Policy Methods for LLM Reasoning
- NeurIPS 2026SH$^2$: A Mathematician-Curated benchmark for Assessing Research-level Math Capabilities of LLMs
- NeurIPS 2026Simulating Students or Sycophantic Problem Solving? On Misconception Faithfulness of LLM Simulators
- NeurIPS 2026Smart Picks in the Dark: Towards Efficient RLVR for Reasoning via Tracing Metacognitive Pivots
- NeurIPS 2026SoDeArena: A Socially-Situated Reasoning Benchmark for Large Language Models
- NeurIPS 2026Solving Every Step Is Not Enough: Milestone Oracles Reveal a Composition Gap in LLM Math Reasoning
- NeurIPS 2026Sparse Attention as a Range Searching Problem: Towards an Inference-Efficient Index for KV Cache
- NeurIPS 2026Sparse Expansion Utility: Identifying and Routing to Pivotal Steps in LLM Reasoning Chains
- NeurIPS 2026SphMind: Towards Robust, Training-Free VLM-based Spatial Reasoning with a 360 Camera
- NeurIPS 2026Stability in Multi-Step Reasoning via Jacobian-based Error Accumulation Analysis
- NeurIPS 2026Stabilizing Knowledge, Promoting Reasoning: Dual-Token Constraints for RLVR
- NeurIPS 2026STAR-Math: Multi-Agent Mathematical Reasoning under Persistent Meta-Strategic Supervision
- NeurIPS 2026State of Thought Enables Endogenous Reasoning
- NeurIPS 2026StateTree: Enhancing Long-term Dialogue Reasoning via Reinforcement Learning
- NeurIPS 2026Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces
- NeurIPS 2026Step-wise Rubric Rewards for LLM Reasoning
- NeurIPS 2026Stepwise Penalization for Length-Efficient Chain-of-Thought Reasoning
- NeurIPS 2026Stop or Restart? Principled Inference Control for Large Reasoning Models via the Pandora's Box
- NeurIPS 2026Strategist: Designing Agentic Reasoning at Scale
- NeurIPS 2026STRIDE: Learnable Stepwise Language Feedback for LLM Reasoning
- NeurIPS 2026Structural Rationale Distillation via Reasoning Space Compression
- NeurIPS 2026TargetSage: Identifying Therapeutic Target Genes with Interpretable and Robust LLM Reasoning
- NeurIPS 2026TARP: Trace-Anchored Regularization Prior for Retaining Stepwise Reasoning
- NeurIPS 2026TaskGround: Structured Executable Task Inference for Full-Scene Household Reasoning
- NeurIPS 2026Teach-to-Reason: Competition-Guided Reasoning with a Self-Improving Teacher
- NeurIPS 2026TERMINATOR: Learning Optimal Exit Points for Early Stopping in Chain-of-Thought 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"}
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。