AI usage in string theory, a case study: String Vacua in the Interior of Moduli Space
Timm Wrase

TL;DR
This paper explores the use of AI in string theory research, focusing on four-dimensional Minkowski vacua in type IIB compactifications, and discusses how AI can aid in analyzing complex models and conjectures.
Contribution
It presents a case study applying AI techniques to analyze string vacua, especially in the context of flux stabilization and the string landscape, building on recent theoretical work.
Findings
Higher-order flux superpotential terms can stabilize previously massless fields.
Isolated Minkowski vacua are identified in the 2^6 model.
Constructed models provide data supporting the tadpole and massless Minkowski conjectures.
Abstract
These proceedings start with a discussion of my recent experiences with large language models and potential implications for their usage in our field. This is followed by an AI generated summary of my talk at the workshop ``Recent Progress in Computational String Geometry,'' held at the Chennai Mathematical Institute in January 2026. The focus is on four-dimensional Minkowski vacua in type IIB compactifications that live deep in the interior of moduli space and admit an exact worldsheet description in terms of Landau--Ginzburg models. The main examples are the and models, mirror to rigid Calabi--Yau threefolds and therefore free of K\"ahler moduli. This makes them ideal laboratories for testing whether fluxes can stabilize all fields and for probing conjectures about the string landscape and the swampland. Based mostly on arXiv:2406.03435, arXiv:2407.16756,…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
