pAI/MSc: ML Theory Research with Humans on the Loop
This addresses the challenge of streamlining research processes for academics in machine learning theory and related fields, but it is incremental as it builds on existing multi-agent concepts.
The authors tackled the problem of reducing human effort in academic research workflows by developing pAI/MSc, a multi-agent system that significantly decreases the human steering needed to produce manuscript drafts from hypotheses, though no concrete numbers are provided.
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.