Collaborative AI agents for autonomous experimental research with solid-state quantum spins

A team led by El Mustapha Mansouri posted an arXiv paper on 29 October 2026 describing an autonomous research laboratory in which large-language-model agents review one another's work and can halt or redirect investigations. Testing the system on ensembles of quantum spins in diamond, the agents derived the minimum number of calibration settings needed to predict responses to a defined family of microwave pulse sequences, then designed experiments to distinguish competing predictions; when repeated reference measurements showed the signal drifting during data collection, the agents treated the initial result as inconclusive and revised the measurement protocol without relaxing acceptance criteria, and the revised experiment met those criteria and supported the theoretical predictions. The authors present the study as evidence that collaborating AI agents can select research questions, derive theoretical results and test their predictions experimentally.

Computer Science Artificial Intelligence Submitted on 29 Oct 2026 Title:Collaborative AI agents for autonomous experimental research with solid-state quantum spins View PDF http://arxiv.org/pdf/2610.40589v1 HTML experimental https://arxiv.org/html/2610.40589v1 Abstract:An autonomous research laboratory could conduct an entire study, from formulating questions to preparing manuscripts. Artificial intelligence AI offers one route towards this goal. Recent AI systems take on several research roles, but may draw conclusions that the evidence does not support. Here, we present an autonomous research laboratory in which agents based on large language models assess one another's work and can stop or redirect investigations. They can generate and reject research questions, require separate theoretical checks and conduct experiments designed to challenge their claims. We demonstrate these capabilities by investigating ensembles of quantum spins in diamond. The agents derived the minimum number of calibration settings needed to predict responses to a defined family of microwave pulse sequences. They checked the result computationally and designed experiments to distinguish competing predictions. An initial experiment agreed with the theoretical predictions, but repeated reference measurements showed that the signal was drifting during data collection. The agents therefore treated the result as inconclusive and revised the measurement protocol without relaxing the acceptance criteria. The revised experiment met those criteria and supported the theoretical predictions. This study demonstrates that collaborating AI agents can select research questions, derive theoretical results and test their predictions experimentally. Submission history From: El Mustapha Mansouri view email http://arxiv.org/show-email/30b29f58/2610.40589 v1 Thu, 29 Oct 2026 17:47:50 UTC 214 KB Additional Features Current browse context: cs.AI References & Citations Loading... Bibliographic and Citation Tools Bibliographic Explorer What is the Explorer? https://info.arxiv.org/labs/showcase.html arxiv-bibliographic-explorer Connected Papers What is Connected Papers? https://www.connectedpapers.com/about Litmaps What is Litmaps? https://www.litmaps.co/ scite Smart Citations What are Smart Citations? https://www.scite.ai/ Code, Data and Media Associated with this Article alphaXiv What is alphaXiv? https://alphaxiv.org/ CatalyzeX Code Finder for Papers What is CatalyzeX? https://www.catalyzex.com DagsHub What is DagsHub? https://dagshub.com/ Gotit.pub What is GotitPub? http://gotit.pub/faq Hugging Face What is Huggingface? https://huggingface.co/huggingface ScienceCast What is ScienceCast? https://sciencecast.org/welcome Demos Recommenders and Search Tools Influence Flower What are Influence Flowers? https://influencemap.cmlab.dev/ CORE Recommender What is CORE? https://core.ac.uk/services/recommender arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs https://info.arxiv.org/labs/index.html .