mlsanityData to 14 Oct 2026

AI for Mathematics: A Cognitive Science Perspective

arXiv 2310.13021 ↗First posted 19 Oct 2023q-bio.NC cs.AIcited by 10

Not on the map. Why?

Abstract (arXiv)

Mathematics is one of the most powerful conceptual systems developed and used by the human species. Dreams of automated mathematicians have a storied history in artificial intelligence (AI). Rapid progress in AI, particularly propelled by advances in large language models (LLMs), has sparked renewed, widespread interest in building such systems. In this work, we reflect on these goals from a textitcognitive science perspective. We call attention to several classical and ongoing research directions from cognitive science, which we believe are valuable for AI practitioners to consider when seeking to build truly human (or superhuman)-level mathematical systems. We close with open discussions and questions that we believe necessitate a multi-disciplinary perspective -- cognitive scientists working in tandem with AI researchers and mathematicians -- as we move toward better mathematical AI systems which not only help us push the frontier of the mathematics, but also offer glimpses into how we as humans are even capable of such great cognitive feats.

Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). Builds on 32 of its 115 references that are in the map. First posted on arXiv 19 Oct 2023.

Builds on

32 of 115 references.

References · 32

  1. 2020Language Models are Few-Shot Learnerscited by 32,419
  2. 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
  3. 2023Reflexion: Language Agents with Verbal Reinforcement Learningcited by 4,276
  4. 2023Let's Verify Step by Stepcited by 3,789
  5. 2022Training Compute-Optimal Large Language Modelscited by 3,019
  6. 2023Sparks of Artificial General Intelligence: Early experiments with GPT-4cited by 2,592
  7. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  8. 2022STaR: Bootstrapping Reasoning With Reasoningcited by 940
  9. 2023MetaMath: Bootstrap Your Own Mathematical Questions for Large Language Modelscited by 735
  10. 2023WizardMath: Empowering Mathematical Reasoning for Large Language Models via Reinforced Evol-Instructcited by 625
  11. 2023Textbooks Are All You Needcited by 569
  12. 2023Faith and Fate: Limits of Transformers on Compositionalitycited by 503
20 more
  1. 2022Emergent World Representations: Exploring a Sequence Model Trained on a Synthetic Taskcited by 431
  2. 2023Augmented Language Models: a Surveycited by 403
  3. 2022Draft, Sketch, and Prove: Guiding Formal Theorem Provers with Informal Proofscited by 291
  4. 2023Mathematical Capabilities of ChatGPTcited by 268
  5. 2023Solving Math Word Problems by Combining Language Models With Symbolic Solverscited by 124
  6. 2023Baldur: Whole-Proof Generation and Repair with Large Language Modelscited by 119
  7. 2023From Word Models to World Models: Translating from Natural Language to the Probabilistic Language of Thoughtcited by 119
  8. 2021Abstraction and Analogy-Making in Artificial Intelligencecited by 103
  9. 2022Thor: Wielding Hammers to Integrate Language Models and Automated Theorem Proverscited by 98
  10. 2022NaturalProver: Grounded Mathematical Proof Generation with Language Modelscited by 72
  11. 2023Evaluating Language Models for Mathematics through Interactionscited by 70
  12. 2023MathChat: Converse to Tackle Challenging Math Problems with LLM Agentscited by 68
  13. 2020Word meaning in minds and machinescited by 51
  14. 2021People construct simplified mental representations to plancited by 47
  15. 2020Understanding Human Intelligence through Human Limitationscited by 33
  16. 2022Humans decompose tasks by trading off utility and computational costcited by 18
  17. 2022Peano: Learning Formal Mathematical Reasoningcited by 15
  18. 2023Testing GPT-4 with Wolfram Alpha and Code Interpreter plug-ins on math and science problemscited by 12
  19. 2022LEMMA: Bootstrapping High-Level Mathematical Reasoning with Learned Symbolic Abstractionscited by 5
  20. 2013A fully automatic problem solver with human-style outputcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2023: 1; 2024: 6; 2025: 2; 2026: 1.

10 papers.

  1. 2024OlympiadBench: A Challenging Benchmark for Promoting AGI with Olympiad-Level Bilingual Multimodal Scientific Problemscited by 1,136
  2. 2024Building Machines that Learn and Think with Peoplecited by 73
  3. 2024VisionGraph: Leveraging Large Multimodal Models for Graph Theory Problems in Visual Contextcited by 31
  4. 2024Data for Mathematical Copilots: Better Ways of Presenting Proofs for Machine Learningcited by 11
  5. 2025AutoMathKG: The automated mathematical knowledge graph based on LLM and vector databasecited by 6
  6. 2024A Triumvirate of AI Driven Theoretical Discoverycited by 5
  7. 2025WirelessMathBench: A Mathematical Modeling Benchmark for LLMs in Wireless Communicationscited by 4
  8. 2024Models Can and Should Embrace the Communicative Nature of Human-Generated Mathcited by 1
  9. 2026From Solvers to Research: Large Language Model-Driven Formal Mathematics at the Research Frontiercited by 1
  10. 2023Understanding the Countably Infinite: Neural Network Models of the Successor Function and its Acquisitioncited by 0