Source record

Published by arXiv cs.HC (T1 source). The original is at https://arxiv.org/abs/2609.12273.

Pipeline notes

The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.

The paper introduces Synthetic TLX, a paradigm for predicting NASA Task Load Index scores via agent simulation before humans perform a task. Three experiments compared agent-generated and human ratings, finding alignment when agents used human personas and active task simulation, though agents and humans diverged on which workload sources they were sensitive to.

Primary research shifting workload assessment from retrospective to predictive. Experimental findings clarify where agent simulation matches human self-report and where it does not.

Cited by

No citations on record.