Synthetic TLX: Forecasting Human Workload Using Agent Simulation
3.60T1 sourcearXiv cs.HC
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.
SummaryThe 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.
Why it mattersPrimary 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.