PACE-SIMS: Checkpoint-Gated Autonomous SIMS Characterization with AI-Agent Quality Control
Abstract
Time-of-flight secondary ion mass spectrometry (ToF-SIMS) is widely used for local chemical investigations across a broad range of materials and systems. However, its operation is expensive in expert time: a trained researcher must supervise the acquisition continuously, tuning parameters as the experiment proceeds, often across a campaign spanning multiple days. Here, we present PACE-SIMS (Pause-Assess-Correct-Execute for SIMS), an agentic workflow that runs a SIMS study as a human-AI collaboration. In this workflow, the researcher specifies the scientific questions and quality requirements, and an AI agent builds the plan and, after approval, executes it autonomously, pausing at checkpoints to judge each measurement and to correct, retry, or escalate. To validate the approach, we applied it to a study of chemical composition in 18O-enriched WOx films. During this randomized, blind two-polarity study (8.1 hours, 35 measurements), the agent applied three rule-governed corrections and diagnosed an unanticipated source excursion without requiring event-specific control logic to be programmed in advance. The same run returned transferable measurement science, including a composition calibration and the deposition's tracer-delivery mechanism, from less than two hours of researcher attention. The developed agentic architecture is not specific to SIMS and can be applied to other analytical techniques, with the primary target being destructive measurements, for which optimization-based methods are poorly suited.
Versions
Related
- Electrostatic control of Li+ density and transport rate in double-gated van der Waals devices
- End-to-end film-based characterization of gated delivery latencies in a spot-scanned synchrotron-based proton therapy system.
- Cross-Platform Autonomous Control of Minimal Kitaev Chains
- Extending the Similarity Spectrum to the SWIR for quality control of above water reflectance measurements
- High-quality multi-focus laser stealth dicing of silicon wafer via precise control of spatial focus and laser energy
BibTeX
@misc{ievlev2026pacesims,
title = {{PACE-SIMS: Checkpoint-Gated Autonomous SIMS Characterization with AI-Agent Quality Control}},
author = {Anton V Ievlev and Heather Hare and Yiyang Li and Sergei V Kalinin},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2608.12277},
eprint = {2608.12277},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2608.12277},
}
RIS
TY - UNPB
TI - PACE-SIMS: Checkpoint-Gated Autonomous SIMS Characterization with AI-Agent Quality Control
AU - Anton V Ievlev
AU - Heather Hare
AU - Yiyang Li
AU - Sergei V Kalinin
PY - 2026
DA - 2026/09/29
PB - arXiv
DO - 10.48550/arxiv.2608.12277
UR - https://arxiv.org/abs/2608.12277
AB - Time-of-flight secondary ion mass spectrometry (ToF-SIMS) is widely used for local chemical investigations across a broad range of materials and systems. However, its operation is expensive in expert time: a trained researcher must supervise the acquisition continuously, tuning parameters as the experiment proceeds, often across a campaign spanning multiple days. Here, we present PACE-SIMS (Pause-Assess-Correct-Execute for SIMS), an agentic workflow that runs a SIMS study as a human-AI collaboration. In this workflow, the researcher specifies the scientific questions and quality requirements, and an AI agent builds the plan and, after approval, executes it autonomously, pausing at checkpoints to judge each measurement and to correct, retry, or escalate. To validate the approach, we applied it to a study of chemical composition in 18O-enriched WOx films. During this randomized, blind two-polarity study (8.1 hours, 35 measurements), the agent applied three rule-governed corrections and diagnosed an unanticipated source excursion without requiring event-specific control logic to be programmed in advance. The same run returned transferable measurement science, including a composition calibration and the deposition's tracer-delivery mechanism, from less than two hours of researcher attention. The developed agentic architecture is not specific to SIMS and can be applied to other analytical techniques, with the primary target being destructive measurements, for which optimization-based methods are poorly suited.
ER -