@inproceedings{jian-etal-2026-exploring,
title = "Exploring Agentic Multimodal Large Language Models: A Survey for {AIS}cientists",
author = "Jian, Jinglin and
Fung, Yi R. and
Zhang, Denghui and
Liang, Yiqian and
Chen, Qingyu and
Lu, Zhiyong and
Wang, Qingyun",
editor = "Zhang, Yue and
Xu, Ruifeng and
Purwarianti, Ayu and
Rong, Tong and
Suzuki, Jun",
booktitle = "Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the {A}sia-Pacific Chapter of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
month = nov,
year = "2026",
address = "Hengqin, China",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.aacl-long.52/",
pages = "1089--1133",
ISBN = "979-8-89176-439-2",
abstract = "Agentic Multimodal Large Language Models (MLLMs) are reshaping scientific discovery. They do more than answer questions: they read multimodal evidence, reason over scientific constraints, use tools, and close parts of the research loop. This survey explains how such systems are built for scientific discovery, moving from multimodal perception to training, inference, evaluation, and human-AI collaboration. Across this pipeline, scientific agents face bottlenecks that generic assistants often hide, including scarce expert annotations, evolving domain structures, complex reasoning, immature tool interfaces, safety and toxicity risks, and unfaithful results. We highlight design choices for turning agentic MLLMs into trustworthy, evidence-grounded collaborators. Curated resources are available at https://github.com/JianJinglin/awesome-agentic-AIScientists."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="jian-etal-2026-exploring">
<titleInfo>
<title>Exploring Agentic Multimodal Large Language Models: A Survey for AIScientists</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jinglin</namePart>
<namePart type="family">Jian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yi</namePart>
<namePart type="given">R</namePart>
<namePart type="family">Fung</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Denghui</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yiqian</namePart>
<namePart type="family">Liang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingyu</namePart>
<namePart type="family">Chen</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhiyong</namePart>
<namePart type="family">Lu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Qingyun</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-11</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)</title>
</titleInfo>
<name type="personal">
<namePart type="given">Yue</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ruifeng</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ayu</namePart>
<namePart type="family">Purwarianti</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Tong</namePart>
<namePart type="family">Rong</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jun</namePart>
<namePart type="family">Suzuki</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">Hengqin, China</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-439-2</identifier>
</relatedItem>
<abstract>Agentic Multimodal Large Language Models (MLLMs) are reshaping scientific discovery. They do more than answer questions: they read multimodal evidence, reason over scientific constraints, use tools, and close parts of the research loop. This survey explains how such systems are built for scientific discovery, moving from multimodal perception to training, inference, evaluation, and human-AI collaboration. Across this pipeline, scientific agents face bottlenecks that generic assistants often hide, including scarce expert annotations, evolving domain structures, complex reasoning, immature tool interfaces, safety and toxicity risks, and unfaithful results. We highlight design choices for turning agentic MLLMs into trustworthy, evidence-grounded collaborators. Curated resources are available at https://github.com/JianJinglin/awesome-agentic-AIScientists.</abstract>
<identifier type="citekey">jian-etal-2026-exploring</identifier>
<location>
<url>https://aclanthology.org/2026.aacl-long.52/</url>
</location>
<part>
<date>2026-11</date>
<extent unit="page">
<start>1089</start>
<end>1133</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Exploring Agentic Multimodal Large Language Models: A Survey for AIScientists
%A Jian, Jinglin
%A Fung, Yi R.
%A Zhang, Denghui
%A Liang, Yiqian
%A Chen, Qingyu
%A Lu, Zhiyong
%A Wang, Qingyun
%Y Zhang, Yue
%Y Xu, Ruifeng
%Y Purwarianti, Ayu
%Y Rong, Tong
%Y Suzuki, Jun
%S Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers)
%D 2026
%8 November
%I Association for Computational Linguistics
%C Hengqin, China
%@ 979-8-89176-439-2
%F jian-etal-2026-exploring
%X Agentic Multimodal Large Language Models (MLLMs) are reshaping scientific discovery. They do more than answer questions: they read multimodal evidence, reason over scientific constraints, use tools, and close parts of the research loop. This survey explains how such systems are built for scientific discovery, moving from multimodal perception to training, inference, evaluation, and human-AI collaboration. Across this pipeline, scientific agents face bottlenecks that generic assistants often hide, including scarce expert annotations, evolving domain structures, complex reasoning, immature tool interfaces, safety and toxicity risks, and unfaithful results. We highlight design choices for turning agentic MLLMs into trustworthy, evidence-grounded collaborators. Curated resources are available at https://github.com/JianJinglin/awesome-agentic-AIScientists.
%U https://aclanthology.org/2026.aacl-long.52/
%P 1089-1133
Markdown (Informal)
[Exploring Agentic Multimodal Large Language Models: A Survey for AIScientists](https://aclanthology.org/2026.aacl-long.52/) (Jian et al., AACL-IJCNLP 2026)
ACL
- Jinglin Jian, Yi R. Fung, Denghui Zhang, Yiqian Liang, Qingyu Chen, Zhiyong Lu, and Qingyun Wang. 2026. Exploring Agentic Multimodal Large Language Models: A Survey for AIScientists. In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics (Volume 1: Long Papers), pages 1089–1133, Hengqin, China. Association for Computational Linguistics.