← News

ResearchSources: arXiv · 18 Nov 2026

StringQFT pairs an 18-volume string theory textbook set with AI research tooling

A new arXiv release describes StringQFT, a large textbook collection on string constructions of quantum field theory that doubles as infrastructure for AI-assisted theoretical physics.

In plain words

Researchers posted a huge set of physics textbooks that also works as a toolkit for AI systems. The books cover how string theory describes quantum field theory, and the package includes benchmarks, search records and calculation tools so AI programs can be tested against or grounded in the material.

What was announced

According to the arXiv abstract, StringQFT comprises 18 volumes, 190 chapters and 3,795 pages, covering topics including brane probes, brane webs, geometric engineering, F-theory constructions, wrapped M5-branes and exact worldsheet constructions. The authors position the collection both as a textbook resource and as infrastructure for AI-assisted theoretical physics.

The AI-facing components are specific. The abstract describes an open-book benchmark inventory of 1,073 items, of which 499 support automatic finite-answer checking, plus 1,371 section records linked to textbook sources and PDF locations for retrieval-augmented generation, accompanied by a local lexical retriever. For agents, the collection exposes 19 calculation tools with specified inputs and finite domains, which the authors say connect tool use to textbook derivations. Training-data preparation is illustrated by 21 private, source-linked examples. The authors illustrate these uses through specific questions, retrieved passages and finite calculations, and the collection is available on GitHub.

What it does not show

  • The evidence is the arXiv abstract only; the reported contents, benchmark items and tools are author claims not verified here, and no independent evaluation of the AI uses is included.

For security and IT teams

Access
The textbook collection and accompanying resources are hosted on GitHub at the repository listed in the abstract.

Sources

Source-support review completed 19 Nov 2026. This story was drafted with AI assistance and checked against retained source passages. Automated checking is not independent verification.

Coverage: arXiv: abstract.

Updates and corrections

No corrections so far.

First published 19 Nov 2026

New to the subject? AI from the Ground Up starts from the beginning.