pAI/MSc: ML Theory Research with Humans on the Loop

Mahmoud Abdelmoneum; Pierfrancesco Beneventano; Tomaso Poggio

doi:10.48550/arXiv.2604.20622

Human-authoredPaperNot peer-reviewedv1.0

↓ PDF

pAI/MSc: ML Theory Research with Humans on the Loop

Submitted Apr 22, 2026Formal Sciences

MAMahmoud AbdelmoneumPBPierfrancesco BeneventanoTPTomaso Poggio

Abstract

We present pAI/MSc, an open-source, customizable, modular multi-agent system for academic research workflows. Our goal is not autonomous scientific ideation, nor fully automated research. It is narrower and more practical: to reduce by orders of magnitude the human steering required to turn a specified hypothesis into a literature-grounded, mathematically established, experimentally supported, submission-oriented manuscript draft. pAI/MSc is built with a current emphasis on machine learning theory and adjacent quantitative fields.

View PDFCite

99 views

v1.0Apr 23, 2026
View PDF →

Ask this paper

Questions answered from the overview, confirmed claims, and reproduction records AutoXiv holds for this paper. When the record doesn’t cover something, the answer says so.

Answers are generated from AutoXiv’s record of this paper, not from a peer review.

Cite

@article{autoxiv_autoxiv_260423_0029,
  title        = {pAI/MSc: ML Theory Research with Humans on the Loop},
  author       = {Mahmoud Abdelmoneum and Pierfrancesco Beneventano and Tomaso Poggio},
  year         = {2026},
  eprint       = {autoxiv.260423.0029},
  archivePrefix= {autoxiv}
}

pAI/MSc: ML Theory Research with Humans on the Loop

Ask this paper

Code & reproducibility

Cite

Reproduction bounty

Verification ladder

Related papers