@inproceedings{sun-etal-2026-towards,
title = "Towards Fluid Consultations: Design and Real-World Evaluation of a Multi-Agent, Full-Duplex Health {AI} Assistant",
author = "Sun, Zhoujian and
Yang, Minghui and
Wang, Jian and
Gu, Jinjie and
Liu, Junwei",
editor = "Atanasova, Pepa and
Haffari, Gholamreza and
Wang, Minghan",
booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.emnlp-industry.36/",
pages = "610--625",
ISBN = "979-8-89176-460-6",
abstract = "Access to reliable health consultation is a critical global challenge. While large language models show promise, their practical utility is typically limited by high input barriers, lack of adaptive response strategies for complex scenarios, and insufficient real-world evaluation. To address these gaps, we present a novel health AI assistant that integrates a low-latency full-duplex voice interface with a Multi-Agent System (MAS). The full-duplex design supports natural turn-taking, significantly lowering interaction barriers and quadrupling average conversation depth from 2.62 to 10.16 turns compared to text-based baselines. Furthermore, our MAS architecture decouples clinical reasoning from general conversation, effectively managing complex queries and boosting clinical performance scores by over 30{\%} compared to single-agent baselines. We conducted the first large-scale analysis of an LLM-based health assistant deployed to the general public ($N > 5,000$), demonstrating superior user engagement and providing empirical evidence on the safety and utility of deploying such systems in realistic environments."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sun-etal-2026-towards">
<titleInfo>
<title>Towards Fluid Consultations: Design and Real-World Evaluation of a Multi-Agent, Full-Duplex Health AI Assistant</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhoujian</namePart>
<namePart type="family">Sun</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghui</namePart>
<namePart type="family">Yang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jian</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinjie</namePart>
<namePart type="family">Gu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Junwei</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-10</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track</title>
</titleInfo>
<name type="personal">
<namePart type="given">Pepa</namePart>
<namePart type="family">Atanasova</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Gholamreza</namePart>
<namePart type="family">Haffari</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Minghan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Budapest, Hungary</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-460-6</identifier>
</relatedItem>
<abstract>Access to reliable health consultation is a critical global challenge. While large language models show promise, their practical utility is typically limited by high input barriers, lack of adaptive response strategies for complex scenarios, and insufficient real-world evaluation. To address these gaps, we present a novel health AI assistant that integrates a low-latency full-duplex voice interface with a Multi-Agent System (MAS). The full-duplex design supports natural turn-taking, significantly lowering interaction barriers and quadrupling average conversation depth from 2.62 to 10.16 turns compared to text-based baselines. Furthermore, our MAS architecture decouples clinical reasoning from general conversation, effectively managing complex queries and boosting clinical performance scores by over 30% compared to single-agent baselines. We conducted the first large-scale analysis of an LLM-based health assistant deployed to the general public (N > 5,000), demonstrating superior user engagement and providing empirical evidence on the safety and utility of deploying such systems in realistic environments.</abstract>
<identifier type="citekey">sun-etal-2026-towards</identifier>
<location>
<url>https://aclanthology.org/2026.emnlp-industry.36/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>610</start>
<end>625</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Towards Fluid Consultations: Design and Real-World Evaluation of a Multi-Agent, Full-Duplex Health AI Assistant
%A Sun, Zhoujian
%A Yang, Minghui
%A Wang, Jian
%A Gu, Jinjie
%A Liu, Junwei
%Y Atanasova, Pepa
%Y Haffari, Gholamreza
%Y Wang, Minghan
%S Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing: Industry Track
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-460-6
%F sun-etal-2026-towards
%X Access to reliable health consultation is a critical global challenge. While large language models show promise, their practical utility is typically limited by high input barriers, lack of adaptive response strategies for complex scenarios, and insufficient real-world evaluation. To address these gaps, we present a novel health AI assistant that integrates a low-latency full-duplex voice interface with a Multi-Agent System (MAS). The full-duplex design supports natural turn-taking, significantly lowering interaction barriers and quadrupling average conversation depth from 2.62 to 10.16 turns compared to text-based baselines. Furthermore, our MAS architecture decouples clinical reasoning from general conversation, effectively managing complex queries and boosting clinical performance scores by over 30% compared to single-agent baselines. We conducted the first large-scale analysis of an LLM-based health assistant deployed to the general public (N > 5,000), demonstrating superior user engagement and providing empirical evidence on the safety and utility of deploying such systems in realistic environments.
%U https://aclanthology.org/2026.emnlp-industry.36/
%P 610-625
Markdown (Informal)
[Towards Fluid Consultations: Design and Real-World Evaluation of a Multi-Agent, Full-Duplex Health AI Assistant](https://aclanthology.org/2026.emnlp-industry.36/) (Sun et al., EMNLP 2026)
ACL