@inproceedings{han-etal-2026-molquest,
title = "{M}ol{Q}uest: A Benchmark for Agentic Evaluation of Abductive Reasoning in Chemical Structure Elucidation",
author = "Han, Taolin and
Wu, Shuang and
Wang, Jinghang and
Yuhao, Zhou and
Lv, Renquan and
Zhao, Bing and
Wei, HU and
Qu, Lin",
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.196/",
pages = "4147--4163",
ISBN = "979-8-89176-462-0",
abstract = "Large language models (LLMs) show growing promise for scientific discovery, yet existing benchmarks rely on static, single-turn QA formats that cannot measure the iterative reasoning and strategic planning required in real research. We introduce MolQuest, an agent-based benchmark that reformulates molecular structure elucidation as a multi-turn interactive task grounded in authentic experimental data. Within a simulated laboratory, the model must actively plan experiments, acquire heterogeneous spectral evidence (NMR, MS, IR) on demand, and iteratively refine structural hypotheses while minimizing unnecessary tool calls{---}mirroring the abductive reasoning workflow of a practicing chemist. We evaluate 16 frontier LLM variants under two settings, yielding 32 model{--}setting configurations, and find that the best Agent-mode result reaches only 51.51{\%} accuracy, while most remain substantially lower. Furthermore, the dynamic paradigm amplifies performance for some models yet degrades others, revealing strategic planning deficiencies invisible to static evaluations. MolQuest provides a reproducible, extensible framework that exposes the critical gap between pattern recognition and genuine scientific reasoning in current LLMs."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="han-etal-2026-molquest">
<titleInfo>
<title>MolQuest: A Benchmark for Agentic Evaluation of Abductive Reasoning in Chemical Structure Elucidation</title>
</titleInfo>
<name type="personal">
<namePart type="given">Taolin</namePart>
<namePart type="family">Han</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Shuang</namePart>
<namePart type="family">Wu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jinghang</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Zhou</namePart>
<namePart type="family">Yuhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Renquan</namePart>
<namePart type="family">Lv</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Bing</namePart>
<namePart type="family">Zhao</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">H</namePart>
<namePart type="given">U</namePart>
<namePart type="family">Wei</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Lin</namePart>
<namePart type="family">Qu</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>Large language models (LLMs) show growing promise for scientific discovery, yet existing benchmarks rely on static, single-turn QA formats that cannot measure the iterative reasoning and strategic planning required in real research. We introduce MolQuest, an agent-based benchmark that reformulates molecular structure elucidation as a multi-turn interactive task grounded in authentic experimental data. Within a simulated laboratory, the model must actively plan experiments, acquire heterogeneous spectral evidence (NMR, MS, IR) on demand, and iteratively refine structural hypotheses while minimizing unnecessary tool calls—mirroring the abductive reasoning workflow of a practicing chemist. We evaluate 16 frontier LLM variants under two settings, yielding 32 model–setting configurations, and find that the best Agent-mode result reaches only 51.51% accuracy, while most remain substantially lower. Furthermore, the dynamic paradigm amplifies performance for some models yet degrades others, revealing strategic planning deficiencies invisible to static evaluations. MolQuest provides a reproducible, extensible framework that exposes the critical gap between pattern recognition and genuine scientific reasoning in current LLMs.</abstract>
<identifier type="citekey">han-etal-2026-molquest</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.196/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>4147</start>
<end>4163</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MolQuest: A Benchmark for Agentic Evaluation of Abductive Reasoning in Chemical Structure Elucidation
%A Han, Taolin
%A Wu, Shuang
%A Wang, Jinghang
%A Yuhao, Zhou
%A Lv, Renquan
%A Zhao, Bing
%A Wei, H. U.
%A Qu, Lin
%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 han-etal-2026-molquest
%X Large language models (LLMs) show growing promise for scientific discovery, yet existing benchmarks rely on static, single-turn QA formats that cannot measure the iterative reasoning and strategic planning required in real research. We introduce MolQuest, an agent-based benchmark that reformulates molecular structure elucidation as a multi-turn interactive task grounded in authentic experimental data. Within a simulated laboratory, the model must actively plan experiments, acquire heterogeneous spectral evidence (NMR, MS, IR) on demand, and iteratively refine structural hypotheses while minimizing unnecessary tool calls—mirroring the abductive reasoning workflow of a practicing chemist. We evaluate 16 frontier LLM variants under two settings, yielding 32 model–setting configurations, and find that the best Agent-mode result reaches only 51.51% accuracy, while most remain substantially lower. Furthermore, the dynamic paradigm amplifies performance for some models yet degrades others, revealing strategic planning deficiencies invisible to static evaluations. MolQuest provides a reproducible, extensible framework that exposes the critical gap between pattern recognition and genuine scientific reasoning in current LLMs.
%U https://aclanthology.org/2026.findings-emnlp.196/
%P 4147-4163
Markdown (Informal)
[MolQuest: A Benchmark for Agentic Evaluation of Abductive Reasoning in Chemical Structure Elucidation](https://aclanthology.org/2026.findings-emnlp.196/) (Han et al., Findings 2026)
ACL
- Taolin Han, Shuang Wu, Jinghang Wang, Zhou Yuhao, Renquan Lv, Bing Zhao, HU Wei, and Lin Qu. 2026. MolQuest: A Benchmark for Agentic Evaluation of Abductive Reasoning in Chemical Structure Elucidation. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 4147–4163, Budapest, Hungary. Association for Computational Linguistics.