Collaborative AI agents for autonomous experimental research with solid-state quantum spins
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.
Related
- Can Autonomous LLM Agents Execute Multireference Quantum Chemistry Calculations?
- Photonics-GCCE: group collaborative-competitive evolution multi-agent framework for universal and autonomous optical design
- Hypothesis-Driven Autonomous Materials Synthesis with Multimodal LLM Agents
- TheoPhysEval: Assessing AI agents at autonomous theoretical physics problem solving
- AutoXRD: Autonomous LLM Agents and Comprehensive Evaluation for Powder Diffraction Analysis
BibTeX
@misc{mansouri2026collaborative,
title = {{Collaborative AI agents for autonomous experimental research with solid-state quantum spins}},
author = {El Mustapha Mansouri and Eikichi Kimura and Masato Koga and Keigo Arai},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.40589},
eprint = {2610.40589},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.40589},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Collaborative AI agents for autonomous experimental research with solid-state quantum spins
AU - El Mustapha Mansouri
AU - Eikichi Kimura
AU - Masato Koga
AU - Keigo Arai
PY - 2026
DA - 2026/10/29
PB - arXiv
DO - 10.48550/arxiv.2610.40589
UR - https://arxiv.org/abs/2610.40589
AB - 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.
ER -