Pedro Henrique Diniz

Conversational AI for Public Administration Form Filling: Evaluating Agentic Architectures for Citizen–Government Interaction

We present a systematic evaluation of conversational agent architectures for filling out administrative forms in European Portuguese. Three primary architectures are compared: a Vanilla LLM, a Fixed-Flow Multi-Agent Pipeline (FF-MAP), and a Planning-Driven Agent System (PDAS), including an enhanced variant with iterati...