mlsanityData to 14 Oct 2026

AI co-mathematician: Accelerating mathematicians with agentic AI

arXiv 2605.06651 ↗First posted 7 May 2026cs.AIcited by 17

On the map: LLM agents and tool use → Educational agents and math problem solving

Abstract (arXiv)

We introduce the AI co-mathematician, a workbench for mathematicians to interactively leverage AI agents to pursue open-ended research. The AI co-mathematician is optimized to provide holistic support for the exploratory and iterative reality of mathematical workflows, including ideation, literature search, computational exploration, theorem proving and theory building. By providing an asynchronous, stateful workspace that manages uncertainty, refines user intent, tracks failed hypotheses, and outputs native mathematical artifacts, the system mirrors human collaborative workflows. In early tests, the AI co-mathematician helped researchers solve open problems, identify new research directions, and uncover overlooked literature references. Besides demonstrating a highly interactive paradigm for AI-assisted mathematical discovery, the AI co-mathematician also achieves state of the art results on hard problem-solving benchmarks, including scoring 48% on FrontierMath Tier 4, a new high score among all AI systems evaluated.

Key facts. Cited by 17 papers in the map (data through 14 Oct 2026). Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use. Builds on 35 of its 66 references that are in the map. First posted on arXiv 7 May 2026.

Builds on

35 of 66 references.

Closest ancestors · 2

Same direction, newest first

  1. 2026The Agentic Researcher: A Practical Guide to AI-Assisted Research in Mathematics and Machine Learning16 Mar
  2. 2026Numina-Lean-Agent: An Open and General Agentic Reasoning System for Formal Mathematics20 Jan

Other references · 33

  1. 2021Training Verifiers to Solve Math Word Problemscited by 10,109
  2. 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Modelscited by 9,379
  3. 2021Measuring Mathematical Problem Solving With the MATH Datasetcited by 5,371
  4. 2022Solving Quantitative Reasoning Problems with Language Modelscited by 1,392
  5. 2024Qwen2.5-Math Technical Report: Toward Mathematical Expert Model via Self-Improvementcited by 1,090
  6. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,071
  7. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 867
  8. 2022Galactica: A Large Language Model for Sciencecited by 744
  9. 2023MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuningcited by 487
  10. 2025The AI Scientist-v2: Workshop-Level Automated Scientific Discovery via Agentic Tree Searchcited by 422
  11. 2025Accelerating scientific discovery with Co-Scientistcited by 401
  12. 2023Llemma: An Open Language Model For Mathematicscited by 388
21 more
  1. 2025DeepSeek-Prover-V2: Advancing Formal Mathematical Reasoning via Reinforcement Learning for Subgoal Decompositioncited by 287
  2. 2024FrontierMath: A Benchmark for Evaluating Advanced Mathematical Reasoning in AIcited by 243
  3. 2025Kimina-Prover Preview: Towards Large Formal Reasoning Models with Reinforcement Learningcited by 180
  4. 2025ShinkaEvolve: Towards Open-Ended And Sample-Efficient Program Evolutioncited by 174
  5. 2024PutnamBench: Evaluating Neural Theorem-Provers on the Putnam Mathematical Competitioncited by 165
  6. 2025Goedel-Prover-V2: Scaling Formal Theorem Proving with Scaffolded Data Synthesis and Self-Correctioncited by 154
  7. 2023LEGO-Prover: Neural Theorem Proving with Growing Librariescited by 109
  8. 2025Towards Robust Mathematical Reasoningcited by 73
  9. 2026AdaEvolve: Adaptive LLM Driven Zeroth-Order Optimizationcited by 60
  10. 2025Aristotle: IMO-level Automated Theorem Provingcited by 58
  11. 2026DeepSearchQA: Bridging the Comprehensiveness Gap for Deep Research Agentscited by 50
  12. 2025Seed-Prover 1.5: Mastering Undergraduate-Level Theorem Proving via Learning from Experiencecited by 44
  13. 2025Early science acceleration experiments with GPT-5cited by 41
  14. 2024HunyuanProver: A Scalable Data Synthesis Framework and Guided Tree Search for Automated Theorem Provingcited by 33
  15. 2026Accelerating Scientific Research with Gemini: Case Studies and Common Techniquescited by 29
  16. 2025Hard2Verify: A Step-Level Verification Benchmark for Open-Ended Frontier Mathcited by 22
  17. 2025Scientific Algorithm Discovery by Augmenting AlphaEvolve with Deep Researchcited by 19
  18. 2025ProofBridge: Auto-Formalization of Natural Language Proofs in Lean via Joint Embeddingscited by 18
  19. 2025Proving Olympiad Inequalities by Synergizing LLMs and Symbolic Reasoningcited by 17
  20. 2026Escaping the Cognitive Well: Efficient Competition Math with Off-the-Shelf Modelscited by 9
  21. 2026Progress in Formalizing Sphere Packing in Dimension 8cited by 9

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 17.

17 papers.

Sort:

By area:

  1. 2026LeanMarathon: Toward Reliable AI Co-Mathematicians through Long-Horizon Lean Autoformalizationcited by 12
  2. 2026Danus: Orchestrating Mathematical Reasoning Agents with Fact-Graph Memorycited by 8
  3. 2026ResearchMath-14K: Scaling Research-Level Mathematics via Agentscited by 2
  4. 2026VALG: An Agentic System for ML Theory Researchcited by 2
  5. 2026The Problem Is the Problem: Towards Scalable Mathematical Discoverycited by 2
  6. 2026Artificial Intelligence for Mathematical Reasoning: An Integrated Survey of Language Models, Neuro-symbolic Systems, and Verified Discoverycited by 1
  7. 2026Extremal Chowla sets and their linear analogues: A human-AI mathematical investigation using Co-Scientistcited by 1
  8. 2026Stellar Colosseum: A Many-Agent Harness for Long-Horizon Research in Mathematics and Theoretical Computer Sciencecited by 1
  9. 2026Every finite group admits a just finite presentationcited by 0
  10. 2026Human agency in initial human-AI proof formalization workflowscited by 0
  11. 2026Stable Menus of Public Goods: AI-Enabled Progresscited by 0
  12. 2026From Meta Idea to Advanced Mathematical Discovery -- Human-AI Co-Discovery of Sign-Embedding Quantum Algorithmscited by 0
5 more
  1. 2026Mathematical Discovery in the Wild: AI-Guided Proofs in Banach Space Theorycited by 0
  2. 2026EULER: Exploring Underused Links with Evidence-Checked Return for Multi-Agent Mathematical Discoverycited by 0
  3. 2026Continuous Optimization for p-adic Modelscited by 0
  4. 2026CAIRN: Dynamic Fact-Intent DAGs for Multi-Agent Explorationcited by 0
  5. 2026GenLimitLib: A Formal Library for Language Generation in the Limit and AI-Assisted Mathematical Researchcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025AI Mathematician: Towards Fully Automated Frontier Mathematical Research
  2. 2025AI Mathematician as a Partner in Advancing Mathematical Discovery -- A Case Study in Homogenization Theory
  3. 2026Iteris: Agentic Research Loops for Computational Mathematics
  4. 2024Mathematics and Machine Creativity: A Survey on Bridging Mathematics with AI
  5. 2026Euler: Towards Human-Centered Multi-Agent Mathematical Discovery
  6. 2026Towards Autonomous Mathematics Research
  7. 2026RMA: an Agentic System for Research-Level Mathematical Problems
  8. 2026Agentic Neurosymbolic Collaboration for Mathematical Discovery: A Case Study in Combinatorial Design