TRAIL: A Platform for Configurable Human--AI Teaming Experiments
3.80T1 sourcearXiv cs.HC
Source record
Published by arXiv cs.HC (T1 source). The original is at https://arxiv.org/abs/2607.12180.
Pipeline notes
The summary and note below are generated by the signal pipeline — they are Beyond Desk’s reading, not quotations from the source.
SummaryPresents TRAIL, a web platform for reproducible human–AI teaming experiments with a configurable AI teammate (Big Five persona, selective participation, dual memory, longitudinal chaining). A six-session classroom deployment with ~51 students showed that a blind persona change produced a double dissociation: cognitive-scaffolding agents drew stronger contribution ratings and closer linguistic alignment; socially-supportive agents produced warmer team climate and lower over-reliance.
Why it mattersDocuments a working experimental platform with classroom deployment evidence that persona-level AI teammate design causally shapes trust, contribution, and over-reliance over time.
Cited by
No citations on record.
