@inproceedings{sakib-etal-2026-thinking,
title = "Thinking Like a Botanist: Challenging Multimodal Language Models with Intent Driven Chain-of-Inquiry",
author = "Sakib, Syed Nazmus and
Haque, Nafiul and
Amin, Shahrear Bin and
Abdullah, Hasan Muhammad and
Hasan, Md Mehedi and
Hossain, Mohammad Zabed and
Arman, Shifat E.",
editor = "Liakata, Maria and
Moreira, Viviane P. and
Zhang, Jiajun and
Jurgens, David",
booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
month = jul,
year = "2026",
address = "San Diego, California, United States",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2026.findings-acl.1741/",
pages = "34862--34892",
ISBN = "979-8-89176-395-1",
abstract = "Vision evaluations are typically done through multi-step processes. In most contemporary fields, experts analyze images using structured, evidence-based adaptive questioning. In plant pathology, botanists inspect leaf images, identify visual cues, infer diagnostic intent, and probe further with targeted questions that adapt to species, symptoms, and severity. This structured probing is crucial for accurate disease diagnosis and treatment formulation. Yet current vision-language models are evaluated on single-turn question answering. To address this gap, we introduce PlantInquiryVQA, a benchmark for studying multi-step, intent-driven visual reasoning in botanical diagnosis. We formalize a Chain of Inquiry framework modeling diagnostic trajectories as ordered question-answer sequences conditioned on grounded visual cues and explicit epistemic intent. We release a dataset of 24,964 expert-curated plant images and 138,078 question-answer pairs annotated with visual grounding, severity labels, and domain-specific reasoning templates. Evaluations on top-tier Multimodal Large Language Models reveal that while they describe visual symptoms adequately, they struggle with safe clinical reasoning and accurate diagnosis. Importantly, structured question-guided inquiry significantly improves diagnostic correctness, reduces hallucination, and increases reasoning efficiency. PlantInquiryVQA provides a foundation for training diagnostic agents that reason like expert botanists rather than static classifiers."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="sakib-etal-2026-thinking">
<titleInfo>
<title>Thinking Like a Botanist: Challenging Multimodal Language Models with Intent Driven Chain-of-Inquiry</title>
</titleInfo>
<name type="personal">
<namePart type="given">Syed</namePart>
<namePart type="given">Nazmus</namePart>
<namePart type="family">Sakib</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Nafiul</namePart>
<namePart type="family">Haque</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shahrear</namePart>
<namePart type="given">Bin</namePart>
<namePart type="family">Amin</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hasan</namePart>
<namePart type="given">Muhammad</namePart>
<namePart type="family">Abdullah</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Md</namePart>
<namePart type="given">Mehedi</namePart>
<namePart type="family">Hasan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mohammad</namePart>
<namePart type="given">Zabed</namePart>
<namePart type="family">Hossain</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shifat</namePart>
<namePart type="given">E</namePart>
<namePart type="family">Arman</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<originInfo>
<dateIssued>2026-07</dateIssued>
</originInfo>
<typeOfResource>text</typeOfResource>
<relatedItem type="host">
<titleInfo>
<title>Findings of the Association for Computational Linguistics: ACL 2026</title>
</titleInfo>
<name type="personal">
<namePart type="given">Maria</namePart>
<namePart type="family">Liakata</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Viviane</namePart>
<namePart type="given">P</namePart>
<namePart type="family">Moreira</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jiajun</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">David</namePart>
<namePart type="family">Jurgens</namePart>
<role>
<roleTerm authority="marcrelator" type="text">editor</roleTerm>
</role>
</name>
<originInfo>
<publisher>Association for Computational Linguistics</publisher>
<place>
<placeTerm type="text">San Diego, California, United States</placeTerm>
</place>
</originInfo>
<genre authority="marcgt">conference publication</genre>
<identifier type="isbn">979-8-89176-395-1</identifier>
</relatedItem>
<abstract>Vision evaluations are typically done through multi-step processes. In most contemporary fields, experts analyze images using structured, evidence-based adaptive questioning. In plant pathology, botanists inspect leaf images, identify visual cues, infer diagnostic intent, and probe further with targeted questions that adapt to species, symptoms, and severity. This structured probing is crucial for accurate disease diagnosis and treatment formulation. Yet current vision-language models are evaluated on single-turn question answering. To address this gap, we introduce PlantInquiryVQA, a benchmark for studying multi-step, intent-driven visual reasoning in botanical diagnosis. We formalize a Chain of Inquiry framework modeling diagnostic trajectories as ordered question-answer sequences conditioned on grounded visual cues and explicit epistemic intent. We release a dataset of 24,964 expert-curated plant images and 138,078 question-answer pairs annotated with visual grounding, severity labels, and domain-specific reasoning templates. Evaluations on top-tier Multimodal Large Language Models reveal that while they describe visual symptoms adequately, they struggle with safe clinical reasoning and accurate diagnosis. Importantly, structured question-guided inquiry significantly improves diagnostic correctness, reduces hallucination, and increases reasoning efficiency. PlantInquiryVQA provides a foundation for training diagnostic agents that reason like expert botanists rather than static classifiers.</abstract>
<identifier type="citekey">sakib-etal-2026-thinking</identifier>
<location>
<url>https://aclanthology.org/2026.findings-acl.1741/</url>
</location>
<part>
<date>2026-07</date>
<extent unit="page">
<start>34862</start>
<end>34892</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T Thinking Like a Botanist: Challenging Multimodal Language Models with Intent Driven Chain-of-Inquiry
%A Sakib, Syed Nazmus
%A Haque, Nafiul
%A Amin, Shahrear Bin
%A Abdullah, Hasan Muhammad
%A Hasan, Md Mehedi
%A Hossain, Mohammad Zabed
%A Arman, Shifat E.
%Y Liakata, Maria
%Y Moreira, Viviane P.
%Y Zhang, Jiajun
%Y Jurgens, David
%S Findings of the Association for Computational Linguistics: ACL 2026
%D 2026
%8 July
%I Association for Computational Linguistics
%C San Diego, California, United States
%@ 979-8-89176-395-1
%F sakib-etal-2026-thinking
%X Vision evaluations are typically done through multi-step processes. In most contemporary fields, experts analyze images using structured, evidence-based adaptive questioning. In plant pathology, botanists inspect leaf images, identify visual cues, infer diagnostic intent, and probe further with targeted questions that adapt to species, symptoms, and severity. This structured probing is crucial for accurate disease diagnosis and treatment formulation. Yet current vision-language models are evaluated on single-turn question answering. To address this gap, we introduce PlantInquiryVQA, a benchmark for studying multi-step, intent-driven visual reasoning in botanical diagnosis. We formalize a Chain of Inquiry framework modeling diagnostic trajectories as ordered question-answer sequences conditioned on grounded visual cues and explicit epistemic intent. We release a dataset of 24,964 expert-curated plant images and 138,078 question-answer pairs annotated with visual grounding, severity labels, and domain-specific reasoning templates. Evaluations on top-tier Multimodal Large Language Models reveal that while they describe visual symptoms adequately, they struggle with safe clinical reasoning and accurate diagnosis. Importantly, structured question-guided inquiry significantly improves diagnostic correctness, reduces hallucination, and increases reasoning efficiency. PlantInquiryVQA provides a foundation for training diagnostic agents that reason like expert botanists rather than static classifiers.
%U https://aclanthology.org/2026.findings-acl.1741/
%P 34862-34892
Markdown (Informal)
[Thinking Like a Botanist: Challenging Multimodal Language Models with Intent Driven Chain-of-Inquiry](https://aclanthology.org/2026.findings-acl.1741/) (Sakib et al., Findings 2026)
ACL
- Syed Nazmus Sakib, Nafiul Haque, Shahrear Bin Amin, Hasan Muhammad Abdullah, Md Mehedi Hasan, Mohammad Zabed Hossain, and Shifat E. Arman. 2026. Thinking Like a Botanist: Challenging Multimodal Language Models with Intent Driven Chain-of-Inquiry. In Findings of the Association for Computational Linguistics: ACL 2026, pages 34862–34892, San Diego, California, United States. Association for Computational Linguistics.