# Mathematical reasoning

Area: [LLM reasoning](https://mlsanity.com/lr/index.md). HTML: https://mlsanity.com/lr/mathematical-reasoning/

## Key facts

- Mathematical reasoning: 759 papers on arXiv since 2020 (data through 14 Oct 2026).
- 142 of its 759 mapped papers (19%) cite “DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models” (2024, arXiv 2402.03300).
- 116 of its 759 mapped papers (15%) cite “Solving Quantitative Reasoning Problems with Language Models” (2022, arXiv 2206.14858).
- 20 new papers 17 Sep–14 Oct.

## Most cited here

- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024), cited by 142 papers here
- [Solving Quantitative Reasoning Problems with Language Models](https://mlsanity.com/paper/2206.14858/) (2022), cited by 116 papers here
- [WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instruct](https://mlsanity.com/paper/2308.09583/) (2023), cited by 99 papers here
- [ToRA: A Tool-Integrated Reasoning Agent for Mathematical Problem Solving](https://mlsanity.com/paper/2309.17452/) (2023), cited by 68 papers here
- [Llemma: An Open Language Model For Mathematics](https://mlsanity.com/paper/2310.10631/) (2023), cited by 68 papers here
- [GSM-Symbolic: Understanding the Limitations of Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2410.05229/) (2024), cited by 58 papers here
- [Scaling Relationship on Learning Mathematical Reasoning with Large Language Models](https://mlsanity.com/paper/2308.01825/) (2023), cited by 51 papers here
- [Large Language Models for Mathematical Reasoning: Progresses and Challenges](https://mlsanity.com/paper/2402.00157/) (2024), cited by 47 papers here
- [MathScale: Scaling Instruction Tuning for Mathematical Reasoning](https://mlsanity.com/paper/2403.02884/) (2024), cited by 42 papers here
- [Omni-MATH: A Universal Olympiad Level Mathematic Benchmark For Large Language Models](https://mlsanity.com/paper/2410.07985/) (2024), cited by 42 papers here

## New (17 Sep–14 Oct)

- [Attention-Graph Curvature for the Verification of Mathematical Reasoning](https://mlsanity.com/paper/2610.16709/) (2026-10-12)
- [ACED: Reference-Anchored Aggregation of Natural-Language and Executable Evidence for Mathematical Reasoning](https://mlsanity.com/paper/2610.16635/) (2026-10-12)
- [MathVis: Can AI Reason through Drawing? A Benchmark for Mathematical Figure Generation](https://mlsanity.com/paper/2610.12954/) (2026-10-09)
- [Which Language Should a Skeleton Speak? Language Choices in Multilingual Reasoning](https://mlsanity.com/paper/2610.09607/) (2026-10-07)
- [Algorithmic Scratchpads and Curriculum Staging for Arithmetic Reasoning in Tiny Transformers](https://mlsanity.com/paper/2610.09003/) (2026-10-06)
- [When Does Longer Reasoning Help? Predicting Mathematical Reasoning Through Discovery and Execution](https://mlsanity.com/paper/2610.05322/) (2026-10-04)
- [Dense Neuro-Symbolic Reasoning in a Unified Geometry State](https://mlsanity.com/paper/2610.04280/) (2026-10-03)
- [The Missing Primitive: Diagnosing and Repairing Mathematical Reasoning in Large Language Models](https://mlsanity.com/paper/2610.02191/) (2026-10-01)
- [Reason in Style: Discovering and Controlling Style in Language Models](https://mlsanity.com/paper/2610.00724/) (2026-09-30)
- [ANI: Adaptive Numerical Injection for Unifying Semantic and Arithmetic Representations in Numerical Reasoning](https://mlsanity.com/paper/2609.39294/) (2026-09-30)
- [Mathematical Transfer in LLMs Follows Reasoning Approach More Than Topic](https://mlsanity.com/paper/2610.00331/) (2026-09-29)
- [Correct Answers, Invalid Traces: What Verifiable Grade-School Math Reveals About Chain-of-Thought Traces](https://mlsanity.com/paper/2609.38107/) (2026-09-29)
- [Beyond Compression: Diagnosing How Post-Training Changes Mathematical Reasoning](https://mlsanity.com/paper/2609.37066/) (2026-09-29)
- [Towards Eliminating Catastrophic Forgetting in the Curriculum Learning of Math Reasoning Tasks](https://mlsanity.com/paper/2609.33655/) (2026-09-27)
- [The Geometry of Logic: Stratification Induces Semantic Structure and Robust Reasoning](https://mlsanity.com/paper/2609.32927/) (2026-09-26)
- [Diagnosing Sampled LLM Reasoning in Formal Geometry: Coverage, Realization, and Validity Evidence](https://mlsanity.com/paper/2609.32924/) (2026-09-26)
- [Solving Every Step Is Not Enough: Milestone Oracles Reveal a Composition Gap in LLM Math Reasoning](https://mlsanity.com/paper/2609.32235/) (2026-09-26)
- [Order-Invariant Answers, Order-Sensitive Representations in Mathematical Reasoning](https://mlsanity.com/paper/2609.28442/) (2026-09-23)
- [Math Reasoning in LLMs is Organized by Approach, Not Topic](https://mlsanity.com/paper/2609.27041/) (2026-09-22)
- [Euston: Training Away Mathematical Sycophancy Without Losing the Mathematics](https://mlsanity.com/paper/2609.23205/) (2026-09-19)