@inproceedings{bian-etal-2025-mira,
title = "{MIRA}: Empowering One-Touch {AI} Services on Smartphones with {MLLM}-based Instruction Recommendation",
author = "Bian, Zhipeng and
Zhu, Jieming and
Xie, Xuyang and
Dai, Quanyu and
Zhao, Zhou and
Dong, Zhenhua",
editor = "Rehm, Georg and
Li, Yunyao",
booktitle = "Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)",
month = jul,
year = "2025",
address = "Vienna, Austria",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2025.acl-industry.103/",
doi = "10.18653/v1/2025.acl-industry.103",
pages = "1457--1465",
ISBN = "979-8-89176-288-6",
abstract = "The rapid advancement of generative AI technologies is driving the integration of diverse AI-powered services into smartphones, transforming how users interact with their devices. To simplify access to predefined AI services, this paper introduces MIRA, a pioneering framework for task instruction recommendation that enables intuitive one-touch AI tasking on smartphones. With MIRA, users can long-press on images or text objects to receive contextually relevant instruction recommendations for executing AI tasks. Our work introduces three key innovations: 1) A multimodal large language model (MLLM)-based recommendation pipeline with structured reasoning to extract key entities, infer user intent, and generate precise instructions; 2) A template-augmented reasoning mechanism that integrates high-level reasoning templates, enhancing task inference accuracy; 3) A prefix-tree-based constrained decoding strategy that restricts outputs to predefined instruction candidates, ensuring coherence and intent alignment. Through evaluation using a real-world annotated datasets and a user study, MIRA has demonstrated substantial improvements in recommendation accuracy. The encouraging results highlight MIRA{'}s potential to revolutionize the way users engage with AI services on their smartphones, offering a more seamless and efficient experience."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="bian-etal-2025-mira">
<titleInfo>
<title>MIRA: Empowering One-Touch AI Services on Smartphones with MLLM-based Instruction Recommendation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Zhipeng</namePart>
<namePart type="family">Bian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jieming</namePart>
<namePart type="family">Zhu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xuyang</namePart>
<namePart type="family">Xie</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Quanyu</namePart>
<namePart type="family">Dai</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhenhua</namePart>
<namePart type="family">Dong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2025-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Georg</namePart>
<namePart type="family">Rehm</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yunyao</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Vienna, Austria</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-288-6</identifier>
</relatedItem>
<abstract>The rapid advancement of generative AI technologies is driving the integration of diverse AI-powered services into smartphones, transforming how users interact with their devices. To simplify access to predefined AI services, this paper introduces MIRA, a pioneering framework for task instruction recommendation that enables intuitive one-touch AI tasking on smartphones. With MIRA, users can long-press on images or text objects to receive contextually relevant instruction recommendations for executing AI tasks. Our work introduces three key innovations: 1) A multimodal large language model (MLLM)-based recommendation pipeline with structured reasoning to extract key entities, infer user intent, and generate precise instructions; 2) A template-augmented reasoning mechanism that integrates high-level reasoning templates, enhancing task inference accuracy; 3) A prefix-tree-based constrained decoding strategy that restricts outputs to predefined instruction candidates, ensuring coherence and intent alignment. Through evaluation using a real-world annotated datasets and a user study, MIRA has demonstrated substantial improvements in recommendation accuracy. The encouraging results highlight MIRA’s potential to revolutionize the way users engage with AI services on their smartphones, offering a more seamless and efficient experience.</abstract>
<identifier type="citekey">bian-etal-2025-mira</identifier>
<identifier type="doi">10.18653/v1/2025.acl-industry.103</identifier>
<location>
<url>https://aclanthology.org/2025.acl-industry.103/</url>
</location>
<part>
<date>2025-07</date>
<extent unit="page">
<start>1457</start>
<end>1465</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MIRA: Empowering One-Touch AI Services on Smartphones with MLLM-based Instruction Recommendation
%A Bian, Zhipeng
%A Zhu, Jieming
%A Xie, Xuyang
%A Dai, Quanyu
%A Zhao, Zhou
%A Dong, Zhenhua
%Y Rehm, Georg
%Y Li, Yunyao
%S Proceedings of the 63rd Annual Meeting of the Association for Computational Linguistics (Volume 6: Industry Track)
%D 2025
%8 July
%I Association for Computational Linguistics
%C Vienna, Austria
%@ 979-8-89176-288-6
%F bian-etal-2025-mira
%X The rapid advancement of generative AI technologies is driving the integration of diverse AI-powered services into smartphones, transforming how users interact with their devices. To simplify access to predefined AI services, this paper introduces MIRA, a pioneering framework for task instruction recommendation that enables intuitive one-touch AI tasking on smartphones. With MIRA, users can long-press on images or text objects to receive contextually relevant instruction recommendations for executing AI tasks. Our work introduces three key innovations: 1) A multimodal large language model (MLLM)-based recommendation pipeline with structured reasoning to extract key entities, infer user intent, and generate precise instructions; 2) A template-augmented reasoning mechanism that integrates high-level reasoning templates, enhancing task inference accuracy; 3) A prefix-tree-based constrained decoding strategy that restricts outputs to predefined instruction candidates, ensuring coherence and intent alignment. Through evaluation using a real-world annotated datasets and a user study, MIRA has demonstrated substantial improvements in recommendation accuracy. The encouraging results highlight MIRA’s potential to revolutionize the way users engage with AI services on their smartphones, offering a more seamless and efficient experience.
%R 10.18653/v1/2025.acl-industry.103
%U https://aclanthology.org/2025.acl-industry.103/
%U https://doi.org/10.18653/v1/2025.acl-industry.103
%P 1457-1465
Markdown (Informal)
[MIRA: Empowering One-Touch AI Services on Smartphones with MLLM-based Instruction Recommendation](https://aclanthology.org/2025.acl-industry.103/) (Bian et al., ACL 2025)
ACL