AINeutralarXiv – CS AI · 18h ago6/10
🧠
"So There's a Catch-22 Here": How Early Adopters Who Build Multi-Agent LLM Systems Conceptualize Transparency
Researchers conducted interviews with 13 early adopters building multi-agent LLM systems at a major technology organization to understand how they conceptualize and practice transparency. The study identifies five key transparency frameworks—reproducibility, debugging, boundary-setting, visualization, and auditing—revealing that transparency in distributed AI architectures is understood as a situated socio-technical practice rather than a single standardized concept.