mlsanityData to 7 Oct 2026

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

arXiv 2604.20622 ↗First posted 22 Apr 2026cs.AI cs.LG cs.MAcited by 2

Not on the map. Why?

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Builds on 37 of its 83 references that are in the map. First posted on arXiv 22 Apr 2026.

Builds on

37 of 83 references.

References · 37

  1. 2023GPQA: A Graduate-Level Google-Proof Q&A Benchmarkcited by 2,748
  2. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  3. 2023Improving Factuality and Reasoning in Language Models through Multiagent Debatecited by 1,739
  4. 2023GAIA: a benchmark for General AI Assistantscited by 1,084
  5. 2024The AI Scientist: Towards Fully Automated Open-Ended Scientific Discoverycited by 1,002
  6. 2025AlphaEvolve: A coding agent for scientific and algorithmic discoverycited by 763
  7. 2017Deep Reinforcement Learning that Matterscited by 727
  8. 2023Enabling Large Language Models to Generate Text with Citationscited by 584
  9. 2023LeanDojo: Theorem Proving with Retrieval-Augmented Language Modelscited by 414
  10. 2025Agent Laboratory: Using LLM Agents as Research Assistantscited by 405
  11. 2021MiniF2F: a cross-system benchmark for formal Olympiad-level mathematicscited by 380
  12. 2023MLAgentBench: Evaluating Language Agents on Machine Learning Experimentationcited by 339
25 more
  1. 2020Improving Reproducibility in Machine Learning Research (A Report from the NeurIPS 2019 Reproducibility Program)cited by 318
  2. 2022OpenAlex: A fully-open index of scholarly works, authors, venues, institutions, and conceptscited by 166
  3. 2024CycleResearcher: Improving Automated Research via Automated Reviewcited by 142
  4. 2018Troubling Trends in Machine Learning Scholarshipcited by 107
  5. 2025Measuring what Matters: Construct Validity in Large Language Model Benchmarkscited by 102
  6. 2024Weak baselines and reporting biases lead to overoptimism in machine learning for fluid-related partial differential equationscited by 87
  7. 2025Mathematical exploration and discovery at scalecited by 66
  8. 2025MLR-Bench: Evaluating AI Agents on Open-Ended Machine Learning Researchcited by 57
  9. 2024Autonomous LLM-driven research from data to human-verifiable research paperscited by 50
  10. 2024ChatCite: LLM Agent with Human Workflow Guidance for Comparative Literature Summarycited by 30
  11. 2022deep-significance - Easy and Meaningful Statistical Significance Testing in the Age of Neural Networkscited by 28
  12. 2026First Proofcited by 26
  13. 2026InternAgent-1.5: A Unified Agentic Framework for Long-Horizon Autonomous Scientific Discoverycited by 24
  14. 2018Over-Optimization of Academic Publishing Metrics: Observing Goodhart's Law in Actioncited by 22
  15. 2022CiteBench: A benchmark for Scientific Citation Text Generationcited by 22
  16. 2015Defining and identifying Sleeping Beauties in sciencecited by 11
  17. 2025ScholarCopilot: Training Large Language Models for Academic Writing with Accurate Citationscited by 9
  18. 2025Build Your Personalized Research Group: A Multiagent Framework for Continual and Interactive Science Automationcited by 8
  19. 2026Reinforced Generation of Combinatorial Structures: Ramsey Numberscited by 8
  20. 2024OverleafCopilot: Empowering Academic Writing in Overleaf with Large Language Modelscited by 7
  21. 2025SurveyGen: Quality-Aware Scientific Survey Generation with Large Language Modelscited by 7
  22. 2026From Agent-Only Social Networks to Autonomous Scientific Research: Lessons from OpenClaw and Moltbook, and the Architecture of ClawdLab and Beach.Sciencecited by 7
  23. 2025PaperDebugger: A Plugin-Based Multi-Agent System for In-Editor Academic Writing, Review, and Editingcited by 5
  24. 2026DeepInnovator: Triggering the Innovative Capabilities of LLMscited by 4
  25. 2025On Learning-Curve Monotonicity for Maximum Likelihood Estimatorscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026The Spectral Dynamics and Noise Geometry of Muoncited by 2
  2. 2026pAI-Econ-claude: A Gated Human-in-the-Loop Multi-Agent Architecture for AI-Assisted Economic Theory Developmentcited by 0