Reframing Conversational Design in HRI: Deliberate Design with AI Scaffolds

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Cao, Shiye, Moon, Jiwon, Xu, Yifan, Liu, Anqi, Huang, Chien-Ming
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914261150728192
author Cao, Shiye
Moon, Jiwon
Xu, Yifan
Liu, Anqi
Huang, Chien-Ming
author_facet Cao, Shiye
Moon, Jiwon
Xu, Yifan
Liu, Anqi
Huang, Chien-Ming
contents Large language models (LLMs) have enabled conversational robots to move beyond constrained dialogue toward free-form interaction. However, without context-specific adaptation, generic LLM outputs can be ineffective or inappropriate. This adaptation is often attempted through prompt engineering, which is non-intuitive and tedious. Moreover, predominant design practice in HRI relies on impression-based, trial-and-error refinement without structured methods or tools, making the process inefficient and inconsistent. To address this, we present the AI-Aided Conversation Engine (ACE), a system that supports the deliberate design of human-robot conversations. ACE contributes three key innovations: 1) an LLM-powered voice agent that scaffolds initial prompt creation to overcome the "blank page problem," 2) an annotation interface that enables the collection of granular and grounded feedback on conversational transcripts, and 3) using LLMs to translate user feedback into prompt refinements. We evaluated ACE through two user studies, examining both designs' experience and end users' interactions with robots designed using ACE. Results show that ACE facilitates the creation of robot behavior prompts with greater clarity and specificity, and that the prompts generated with ACE lead to higher-quality human-robot conversational interactions.
format Preprint
id arxiv_https___arxiv_org_abs_2601_12084
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Reframing Conversational Design in HRI: Deliberate Design with AI Scaffolds
Cao, Shiye
Moon, Jiwon
Xu, Yifan
Liu, Anqi
Huang, Chien-Ming
Human-Computer Interaction
Robotics
Large language models (LLMs) have enabled conversational robots to move beyond constrained dialogue toward free-form interaction. However, without context-specific adaptation, generic LLM outputs can be ineffective or inappropriate. This adaptation is often attempted through prompt engineering, which is non-intuitive and tedious. Moreover, predominant design practice in HRI relies on impression-based, trial-and-error refinement without structured methods or tools, making the process inefficient and inconsistent. To address this, we present the AI-Aided Conversation Engine (ACE), a system that supports the deliberate design of human-robot conversations. ACE contributes three key innovations: 1) an LLM-powered voice agent that scaffolds initial prompt creation to overcome the "blank page problem," 2) an annotation interface that enables the collection of granular and grounded feedback on conversational transcripts, and 3) using LLMs to translate user feedback into prompt refinements. We evaluated ACE through two user studies, examining both designs' experience and end users' interactions with robots designed using ACE. Results show that ACE facilitates the creation of robot behavior prompts with greater clarity and specificity, and that the prompts generated with ACE lead to higher-quality human-robot conversational interactions.
title Reframing Conversational Design in HRI: Deliberate Design with AI Scaffolds
topic Human-Computer Interaction
Robotics
url https://arxiv.org/abs/2601.12084