A Modern System Recipe for Situated Embodied Human-Robot Conversation with Real-Time Multimodal LLMs and Tool-Calling

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Lee, Dong Won, Gillet, Sarah, Morency, Louis-Philippe, Breazeal, Cynthia, Park, Hae Won
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914304982253568
author Lee, Dong Won
Gillet, Sarah
Morency, Louis-Philippe
Breazeal, Cynthia
Park, Hae Won
author_facet Lee, Dong Won
Gillet, Sarah
Morency, Louis-Philippe
Breazeal, Cynthia
Park, Hae Won
contents Situated embodied conversation requires robots to interleave real-time dialogue with active perception: deciding what to look at, when to look, and what to say under tight latency constraints. We present a simple, minimal system recipe that pairs a real-time multimodal language model with a small set of tool interfaces for attention and active perception. We study six home-style scenarios that require frequent attention shifts and increasing perceptual scope. Across four system variants, we evaluate turn-level tool-decision correctness against human annotations and collect subjective ratings of interaction quality. Results indicate that real-time multimodal large language models and tool use for active perception is a promising direction for practical situated embodied conversation.
format Preprint
id arxiv_https___arxiv_org_abs_2602_04157
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle A Modern System Recipe for Situated Embodied Human-Robot Conversation with Real-Time Multimodal LLMs and Tool-Calling
Lee, Dong Won
Gillet, Sarah
Morency, Louis-Philippe
Breazeal, Cynthia
Park, Hae Won
Robotics
Situated embodied conversation requires robots to interleave real-time dialogue with active perception: deciding what to look at, when to look, and what to say under tight latency constraints. We present a simple, minimal system recipe that pairs a real-time multimodal language model with a small set of tool interfaces for attention and active perception. We study six home-style scenarios that require frequent attention shifts and increasing perceptual scope. Across four system variants, we evaluate turn-level tool-decision correctness against human annotations and collect subjective ratings of interaction quality. Results indicate that real-time multimodal large language models and tool use for active perception is a promising direction for practical situated embodied conversation.
title A Modern System Recipe for Situated Embodied Human-Robot Conversation with Real-Time Multimodal LLMs and Tool-Calling
topic Robotics
url https://arxiv.org/abs/2602.04157