human-computer interaction

TRAIL: A Platform for Configurable Human--AI Teaming Experiments

arXiv:2607.12180

summary

TRAIL is a web platform that lets researchers configure AI teammates—defining their personality, communication style, and interaction timing—to run reproducible, longitudinal human‑AI teaming experiments and export detailed analytics.

Abstract

An AI teammate's design properties (personality, communication style, when it speaks) can shape a team's trust, coordination, and decisions. Studying this rigorously demands infrastructure no existing tool provides: reproducible configuration of an AI teammate embedded in instrumented, real-time collaboration sustained over time. We present the Team Research and AI Integration Lab (TRAIL), a web platform that makes the AI teammate a configurable, reproducible design object, pairing a Big Five persona with a selective-participation message pipeline, dual memory, chained longitudinal experiments, and export-ready analytics. In a real six-session classroom deployment (about 51 students), TRAIL sustained longitudinal chaining, held the AI to a stable minority of the conversation, and enabled export-driven AI-human text-similarity analysis. A single blind persona change produced a design-consistent double dissociation: a cognitive-scaffolding agent drew stronger contribution ratings and closer linguistic alignment; a socially-supportive agent, a warmer team climate and lower over-reliance.

Topics & keywords

#human-ai teaming#configurable AI agents#personality modeling#longitudinal collaboration studies#trust and coordinationBig Five personaselective participation pipelinedual memory architecturetext similarity analysisweb-based experiment platform
TRAIL: A Platform for Configurable Human--AI Teaming Experiments · wovepaper