@inproceedings{bu-etal-2026-cabinproact,
title = "{C}abin{P}ro{A}ct: Visually Triggered Proactive Intervention for Intelligent Cabin Agents",
author = "Bu, Chengqing and
Qu, Mengxue and
Ma, Mingming and
Huang, Yuyao and
Zhao, Yao and
Wei, Yunchao",
editor = "Lee, Hung-Yi and
Dev, Sunipa and
Li, Jessy and
Elliott, Desmond",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {EMNLP} 2026",
month = oct,
year = "2026",
address = "Budapest, Hungary",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-emnlp.1568/",
pages = "33392--33413",
ISBN = "979-8-89176-462-0",
abstract = "Traditional in-vehicle agents mainly follow an instruction-following paradigm, where actions are executed only after explicit user commands. However, real-world cabin scenarios often require agents to proactively determine whether intervention is necessary by jointly reasoning over visual and state inputs. To address this gap, we propose CabinProAct, a multimodal benchmark for proactive intelligent cabin agents. In this setting, agents must jointly reason over in-cabin and out-cabin visual information, vehicle states, and executable APIs to autonomously decide whether to intervene and generate corresponding actions. We further introduce an execution-verification-based synthetic data generation framework to automatically construct execution-consistent proactive interaction data. We evaluate six state-of-the-art multimodal models. The results indicate that execution-grounded synthetic supervision effectively transfers to real-world in-cabin settings, enabling more robust proactive responses in real-world cabin scenarios."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bu-etal-2026-cabinproact">
<titleInfo>
<title>CabinProAct: Visually Triggered Proactive Intervention for Intelligent Cabin Agents</title>
</titleInfo>
<name type="personal">
<namePart type="given">Chengqing</namePart>
<namePart type="family">Bu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mengxue</namePart>
<namePart type="family">Qu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingming</namePart>
<namePart type="family">Ma</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuyao</namePart>
<namePart type="family">Huang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yao</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunchao</namePart>
<namePart type="family">Wei</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>Findings of the Association for Computational Linguistics: EMNLP 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Hung-Yi</namePart>
<namePart type="family">Lee</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Sunipa</namePart>
<namePart type="family">Dev</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jessy</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Desmond</namePart>
<namePart type="family">Elliott</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">979-8-89176-462-0</identifier>
</relatedItem>
<abstract>Traditional in-vehicle agents mainly follow an instruction-following paradigm, where actions are executed only after explicit user commands. However, real-world cabin scenarios often require agents to proactively determine whether intervention is necessary by jointly reasoning over visual and state inputs. To address this gap, we propose CabinProAct, a multimodal benchmark for proactive intelligent cabin agents. In this setting, agents must jointly reason over in-cabin and out-cabin visual information, vehicle states, and executable APIs to autonomously decide whether to intervene and generate corresponding actions. We further introduce an execution-verification-based synthetic data generation framework to automatically construct execution-consistent proactive interaction data. We evaluate six state-of-the-art multimodal models. The results indicate that execution-grounded synthetic supervision effectively transfers to real-world in-cabin settings, enabling more robust proactive responses in real-world cabin scenarios.</abstract>
<identifier type="citekey">bu-etal-2026-cabinproact</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1568/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>33392</start>
<end>33413</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CabinProAct: Visually Triggered Proactive Intervention for Intelligent Cabin Agents
%A Bu, Chengqing
%A Qu, Mengxue
%A Ma, Mingming
%A Huang, Yuyao
%A Zhao, Yao
%A Wei, Yunchao
%Y Lee, Hung-Yi
%Y Dev, Sunipa
%Y Li, Jessy
%Y Elliott, Desmond
%S Findings of the Association for Computational Linguistics: EMNLP 2026
%D 2026
%8 October
%I Association for Computational Linguistics
%C Budapest, Hungary
%@ 979-8-89176-462-0
%F bu-etal-2026-cabinproact
%X Traditional in-vehicle agents mainly follow an instruction-following paradigm, where actions are executed only after explicit user commands. However, real-world cabin scenarios often require agents to proactively determine whether intervention is necessary by jointly reasoning over visual and state inputs. To address this gap, we propose CabinProAct, a multimodal benchmark for proactive intelligent cabin agents. In this setting, agents must jointly reason over in-cabin and out-cabin visual information, vehicle states, and executable APIs to autonomously decide whether to intervene and generate corresponding actions. We further introduce an execution-verification-based synthetic data generation framework to automatically construct execution-consistent proactive interaction data. We evaluate six state-of-the-art multimodal models. The results indicate that execution-grounded synthetic supervision effectively transfers to real-world in-cabin settings, enabling more robust proactive responses in real-world cabin scenarios.
%U https://aclanthology.org/2026.findings-emnlp.1568/
%P 33392-33413
Markdown (Informal)
[CabinProAct: Visually Triggered Proactive Intervention for Intelligent Cabin Agents](https://aclanthology.org/2026.findings-emnlp.1568/) (Bu et al., Findings 2026)
ACL