Auditable Human-Agent Teams for Autonomous X-ray Experimentation

The paper reports on closed‑loop autonomous synchrotron X‑ray experiments performed on nanoparticle superlattices using a coding‑agent infrastructure. It presents detailed human‑agent and agent‑agent transcripts that allow an audit of decision provenance and the division of cognitive labor. Across three experiments, the study quantifies the proportion of messages involving interpretation, judgment, methodological input, and error corrections, showing how contributions shift as the experiments progress.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv AI.

• agents