Agentic AI

I am exploring how agentic AI can support mathematics at two complementary stages: discovering and checking mathematical arguments, and communicating difficult ideas so that researchers can learn them more quickly and interactively.

Collaborative experiment

Agentic AI for mathematics

Agents for proof discovery and verification

Can an agent help develop a proof while preserving the standards of mathematical argument? I contribute to pipeline-math, a research-stage collaboration spanning learning theory, algebra, number theory, and graph theory.

In the project, GPT-5.5 Pro generates candidate proofs through a prover–verifier workflow. Human contributors then polish and check the resulting write-ups, and selected results are formalized in Lean 4. I contributed to the project’s work on Erdős Problem 477.

Propose

Generate and revise candidate proof strategies.

Check

Use agent critique together with human mathematical review.

Formalize

Translate selected arguments into machine-checked Lean proofs.

Research status: this is a public experimental collection. Only selected results are currently formalized, and the repository explicitly labels partial results.

Explore pipeline-math on GitHub
Research prototype

Agentic AI for mathematical communication

From a frontier paper to an interruptible lecture

AI for mathematics can help produce new arguments. A complementary challenge is how those arguments move between people. A difficult paper can demand hours of focused work simply to reconstruct its notation, prerequisites, and proof strategy.

Virtual290 asks what happens when an agent is given a frontier paper and asked to teach it the way we would teach a graduate lecture: working through a theorem on a blackboard, explaining it aloud, and pausing whenever the learner has a question.

Show

Write mathematical arguments on a chalk-style board.

Explain

Synchronize narration, notation, annotation, and pointing.

Discuss

Pause for voice or text questions, revisit a step, and resume.

Research status: synchronized lectures and live questions work in the current prototype; lectures are still authored by hand. An automated paper-to-lecture compiler is the next milestone.

Explore Virtual290 on GitHub

One research agenda

Discover, verify, explain, and question.

Mathematical agents should not only search for answers. They should help us establish confidence in those answers, make difficult reasoning legible to other researchers, and create space for the questions through which understanding develops.

DiscoverVerifyExplainQuestion

I welcome feedback and collaborators interested in either side of this exploration.