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

arXiv: https://arxiv.org/abs/2604.20622 · HTML: https://mlsanity.com/paper/2604.20622/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 37 of its 83 references that are in the map.
- First posted on arXiv 22 Apr 2026.

## Builds on (most cited first, 30 of 37)

- [GPQA: A Graduate-Level Google-Proof Q&A Benchmark](https://mlsanity.com/paper/2311.12022/) (2023)
- [Shortcut Learning in Deep Neural Networks](https://mlsanity.com/paper/2004.07780/) (2020)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [The AI Scientist: Towards Fully Automated Open-Ended Scientific Discovery](https://mlsanity.com/paper/2408.06292/) (2024)
- [AlphaEvolve: A coding agent for scientific and algorithmic discovery](https://mlsanity.com/paper/2506.13131/) (2025)
- [Deep Reinforcement Learning that Matters](https://mlsanity.com/paper/1709.06560/) (2017)
- [Enabling Large Language Models to Generate Text with Citations](https://mlsanity.com/paper/2305.14627/) (2023)
- [LeanDojo: Theorem Proving with Retrieval-Augmented Language Models](https://mlsanity.com/paper/2306.15626/) (2023)
- [Agent Laboratory: Using LLM Agents as Research Assistants](https://mlsanity.com/paper/2501.04227/) (2025)
- [MiniF2F: a cross-system benchmark for formal Olympiad-level mathematics](https://mlsanity.com/paper/2109.00110/) (2021)
- [MLAgentBench: Evaluating Language Agents on Machine Learning Experimentation](https://mlsanity.com/paper/2310.03302/) (2023)
- [Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)](https://mlsanity.com/paper/2003.12206/) (2020)
- [OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and concepts](https://mlsanity.com/paper/2205.01833/) (2022)
- [CycleResearcher: Improving Automated Research via Automated Review](https://mlsanity.com/paper/2411.00816/) (2024)
- [Measuring what Matters: Construct Validity in Large Language Model Benchmarks](https://mlsanity.com/paper/2511.04703/) (2025)
- [Troubling Trends in Machine Learning Scholarship](https://mlsanity.com/paper/1807.03341/) (2018)
- [Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equations](https://mlsanity.com/paper/2407.07218/) (2024)
- [Mathematical exploration and discovery at scale](https://mlsanity.com/paper/2511.02864/) (2025)
- [MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Research](https://mlsanity.com/paper/2505.19955/) (2025)
- [Autonomous LLM-driven research from data to human-verifiable research papers](https://mlsanity.com/paper/2404.17605/) (2024)
- [First Proof](https://mlsanity.com/paper/2602.05192/) (2026)
- [ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summary](https://mlsanity.com/paper/2403.02574/) (2024)
- [deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networks](https://mlsanity.com/paper/2204.06815/) (2022)
- [InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discovery](https://mlsanity.com/paper/2602.08990/) (2026)
- [Over-Optimization of Academic Publishing Metrics: Observing Goodhart's Law in Action](https://mlsanity.com/paper/1809.07841/) (2018)
- [CiteBench: A benchmark for Scientific Citation Text Generation](https://mlsanity.com/paper/2212.09577/) (2022)
- [Defining and identifying Sleeping Beauties in science](https://mlsanity.com/paper/1505.06454/) (2015)
- [ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citations](https://mlsanity.com/paper/2504.00824/) (2025)
- [Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automation](https://mlsanity.com/paper/2510.15624/) (2025)

## Built on by (most cited first, 2 of 2)

- [The Spectral Dynamics and Noise Geometry of Muon](https://mlsanity.com/paper/2606.08388/) (2026)
- [pAI-Econ-claude: A Gated Human-in-the-Loop Multi-Agent Architecture for AI-Assisted Economic Theory Development](https://mlsanity.com/paper/2607.21268/) (2026)

## Abstract (arXiv)

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.