MMODELYST
Papers/MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes
PAP

MIST: Multimodal Interactive Speech-based Tool-calling Conversational Assistants for Smart Homes

May 7, 2026

arXiv
Abstract

The rise of Internet of Things (IoT) devices in the physical world necessitates voice-based interfaces capable of handling complex user experiences. While modern Large Language Models (LLMs) already demonstrate strong tool-usage capabilities, modeling real-world IoT devices presents a difficult, understudied challenge which combines modeling spatiotemporal constraints with speech inputs, dynamic state tracking, and mixed-initiative interaction patterns. We introduce MIST (the Multimodal Interactive Speech-based Tool-calling Dataset), a synthetic multi-turn, voice-driven code generation task that operates over IoT devices. We find that there is a significant gap between open- and closed-weight multimodal LLMs on MIST, and that even frontier closed-weight LLMs have substantial headroom. We release MIST and an extensible data generation framework to build related datasets in order to facilitate research on mixed-initiative voice assistants which reason about physical world constraints.

Select text to highlight · click a highlight to remove · saved in this browser only
Authors
Maximillian Chen, Xuanming Zhang, Michael Peng, Zhou Yu, Alexandros Papangelis, Yohan Jo
Your notes (browser-local)
saved
arXiv:2605.06897