# Agentic AI for Scientific Reasoning in Autonomous Quantum Sensing Experiments

arXiv: https://arxiv.org/abs/2607.25145 · HTML: https://mlsanity.com/paper/2607.25145/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Placed in Medical and scientific domain agents, one of 16 directions in LLM agents and tool use.
- Builds on 6 of its 23 references that are in the map.
- First posted on arXiv 27 Jul 2026.

## Placed in

- LLM agents and tool use / [Medical and scientific domain agents](https://mlsanity.com/agents/medical-and-scientific-domain-agents/)

## Builds on (most cited first, 6 of 6)

- [Accelerating scientific discovery with Co-Scientist](https://mlsanity.com/paper/2502.18864/) (2025)
- [AgentMD: Empowering Language Agents for Risk Prediction with Large-Scale Clinical Tool Learning](https://mlsanity.com/paper/2402.13225/) (2024)
- [Agents for self-driving laboratories applied to quantum computing](https://mlsanity.com/paper/2412.07978/) (2024)
- [QCalEval: Benchmarking Vision-Language Models for Quantum Calibration Plot Understanding](https://mlsanity.com/paper/2604.25884/) (2026)
- [AI Agents Can Already Autonomously Perform Experimental High Energy Physics](https://mlsanity.com/paper/2603.20179/) (2026)
- [LLM-based Multi-Agent Copilot for Quantum Sensor](https://mlsanity.com/paper/2508.05421/) (2025)

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

- [Provably Efficient Self-Calibrating Quantum Fault Tolerance](https://mlsanity.com/paper/2608.05686/) (2026)
- [Evaluating Verified Autonomy in Quantum Engineering](https://mlsanity.com/paper/2609.17439/) (2026)

## Abstract (arXiv)

We implement an agentic AI workflow built around a large language model (LLM) agent for autonomous experiments with nitrogen-vacancy (NV) centers in diamond. NV centers are a widely used platform for quantum sensing, and the ability to control many measurements from a computer makes NV experiments a natural setting for autonomous workflows. We make two main contributions. First, we demonstrate an autonomous NV experiment workflow that combines persistent project records, quantitative calculation and data analysis tools, and deterministic experiment control. In one autonomous experiment, the agent selected a single NV center, calibrated its resonant frequency, measured (T2^ast) with Ramsey measurements, and added a Carr--Purcell--Meiboom--Gill (CPMG) measurement to check a weak feature that could be related to nearby (13C). Second, we introduce two offline benchmarks that evaluate the agent's reasoning separately from laboratory execution. We evaluated both benchmarks with GPT-5.4, GPT-5.5, and GPT-5.6 Sol. In the Ramsey checkpoint benchmark, greater reasoning effort generally improved recognition of a residual resonance calibration offset. By contrast, in the pulsed optically detected magnetic resonance (pODMR) data evaluation benchmark, pulse sequence information alone produced more false positive resonance judgments at higher reasoning effort. Requiring an expected signal calculation kept false positive rates low across all three models and reasoning settings. The results suggest a clear division of labor for autonomous experiments. The agent forms scientific hypotheses and uses quantitative tools to evaluate data, while deterministic code controls the hardware and enforces safety constraints.