Designing Explainable Conversational Agentic Systems for Guarani Speakers

Samantha Adorno, Akshata Kishore Moharir, Ratna Kandala

Keywords: Conversational AI, Oral-first interaction, LLM, Low-resource languages, Diglossia, Guaraní, Culturally grounded AI, Multi-Agent Systems, Indigenous data governance

TL;DR: Conversational Agentic Systems for Guarani Speakers

Abstract: Artificial intelligence systems are often presented as universal, yet their interaction paradigms remain predominantly text-first, limiting alignment with primarily oral languages and communicative practices. Using Guarani, an official and widely spoken language of Paraguay, as a motivating case, this work examines how language support risks remaining symbolic when spoken interaction is reduced to a speech-to-text interface. We explore an oral-first, multi-agent framing in which turn-taking, repair, shared context, and governance are treated as core components of interaction rather than peripheral features. By separating language understanding from conversation state and permission mechanisms, the architecture makes conversational structure and control explicit, enabling reasoning over interaction dynamics rather than isolated commands.

Paper Format Check: Yes

Submission Type: Extended Abstract (non-archival)

Attendance: I plan to present virtually (only for unavoidable circumstances such as visa issues)

Presenter Name: Samantha Adorno

Presenter Email: [e-mail]

Email Sharing: We authorize the sharing of all author emails with Program Chairs.

Data Release: We authorize the release of our submission and author names to the public in the event of acceptance.

Submission Number: 6