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

TL;DR

pAI/MSc is an open-source multi-agent system designed to significantly reduce human effort in transforming hypotheses into research manuscripts within machine learning theory.

Contribution

It introduces a practical, modular system tailored for research workflows that minimizes human steering in scientific writing and hypothesis testing.

Findings

Reduces human effort in research manuscript creation by orders of magnitude.

Focuses on machine learning theory and related quantitative fields.

Provides a customizable, open-source platform for research automation.

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.