@inproceedings{zhuang-etal-2026-mppreasoner,
title = "{M}pp{R}easoner: Reasoning-Enhanced Large Language Models for Molecular Property Prediction",
author = "Zhuang, Jiaxi and
Shi, Yaorui and
Hou, Jue and
Ye, Mingwei and
Xu, Mingjun and
Su, Yuming and
Zhang, Linfeng and
Qian, Ying and
Zhang, Linfeng and
Ke, Guolin and
Cai, Hengxing",
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.1796/",
pages = "38399--38421",
ISBN = "979-8-89176-462-0",
abstract = "Molecular property prediction is fundamental to drug discovery and materials science, yet existing models suffer from limited interpretability and poor cross-task generalization. Without explainable chemical rationales, accurate predictions alone are insufficient for guiding costly downstream experiments. We propose $\textbf{MppReasoner}$, a multimodal large language model that incorporates verifiable chemical reasoning for molecular property prediction. Built on Qwen2.5-VL-7B-Instruct, MppReasoner integrates 2D molecular images with SMILES strings through a two-stage training strategy: supervised fine-tuning (SFT) on 16,000 expert-guided reasoning trajectories, followed by Reinforcement Learning from Principle-Guided Rewards (RLPGR). RLPGR applies rule-based rewards verified by RDKit to evaluate chemical principle usage, structural analysis, and logical consistency, providing objective feedback without human preference labels. Experiments across 8 benchmark datasets show that MppReasoner outperforms the strongest baseline by 2.95{\%} and 5.49{\%} on in-distribution and out-of-distribution tasks, respectively. Beyond predictive accuracy, MppReasoner generates chemically grounded reasoning traces, with expert evaluation confirming high reasoning quality across three assessed dimensions. Code is available at https://github.com/Jesse-zjx/MPPReasoner."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="zhuang-etal-2026-mppreasoner">
<titleInfo>
<title>MppReasoner: Reasoning-Enhanced Large Language Models for Molecular Property Prediction</title>
</titleInfo>
<name type="personal">
<namePart type="given">Jiaxi</namePart>
<namePart type="family">Zhuang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yaorui</namePart>
<namePart type="family">Shi</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Jue</namePart>
<namePart type="family">Hou</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingwei</namePart>
<namePart type="family">Ye</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Mingjun</namePart>
<namePart type="family">Xu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yuming</namePart>
<namePart type="family">Su</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Linfeng</namePart>
<namePart type="family">Zhang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Ying</namePart>
<namePart type="family">Qian</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Guolin</namePart>
<namePart type="family">Ke</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Hengxing</namePart>
<namePart type="family">Cai</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>Molecular property prediction is fundamental to drug discovery and materials science, yet existing models suffer from limited interpretability and poor cross-task generalization. Without explainable chemical rationales, accurate predictions alone are insufficient for guiding costly downstream experiments. We propose MppReasoner, a multimodal large language model that incorporates verifiable chemical reasoning for molecular property prediction. Built on Qwen2.5-VL-7B-Instruct, MppReasoner integrates 2D molecular images with SMILES strings through a two-stage training strategy: supervised fine-tuning (SFT) on 16,000 expert-guided reasoning trajectories, followed by Reinforcement Learning from Principle-Guided Rewards (RLPGR). RLPGR applies rule-based rewards verified by RDKit to evaluate chemical principle usage, structural analysis, and logical consistency, providing objective feedback without human preference labels. Experiments across 8 benchmark datasets show that MppReasoner outperforms the strongest baseline by 2.95% and 5.49% on in-distribution and out-of-distribution tasks, respectively. Beyond predictive accuracy, MppReasoner generates chemically grounded reasoning traces, with expert evaluation confirming high reasoning quality across three assessed dimensions. Code is available at https://github.com/Jesse-zjx/MPPReasoner.</abstract>
<identifier type="citekey">zhuang-etal-2026-mppreasoner</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1796/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>38399</start>
<end>38421</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T MppReasoner: Reasoning-Enhanced Large Language Models for Molecular Property Prediction
%A Zhuang, Jiaxi
%A Shi, Yaorui
%A Hou, Jue
%A Ye, Mingwei
%A Xu, Mingjun
%A Su, Yuming
%A Zhang, Linfeng
%A Qian, Ying
%A Ke, Guolin
%A Cai, Hengxing
%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 zhuang-etal-2026-mppreasoner
%X Molecular property prediction is fundamental to drug discovery and materials science, yet existing models suffer from limited interpretability and poor cross-task generalization. Without explainable chemical rationales, accurate predictions alone are insufficient for guiding costly downstream experiments. We propose MppReasoner, a multimodal large language model that incorporates verifiable chemical reasoning for molecular property prediction. Built on Qwen2.5-VL-7B-Instruct, MppReasoner integrates 2D molecular images with SMILES strings through a two-stage training strategy: supervised fine-tuning (SFT) on 16,000 expert-guided reasoning trajectories, followed by Reinforcement Learning from Principle-Guided Rewards (RLPGR). RLPGR applies rule-based rewards verified by RDKit to evaluate chemical principle usage, structural analysis, and logical consistency, providing objective feedback without human preference labels. Experiments across 8 benchmark datasets show that MppReasoner outperforms the strongest baseline by 2.95% and 5.49% on in-distribution and out-of-distribution tasks, respectively. Beyond predictive accuracy, MppReasoner generates chemically grounded reasoning traces, with expert evaluation confirming high reasoning quality across three assessed dimensions. Code is available at https://github.com/Jesse-zjx/MPPReasoner.
%U https://aclanthology.org/2026.findings-emnlp.1796/
%P 38399-38421
Markdown (Informal)
[MppReasoner: Reasoning-Enhanced Large Language Models for Molecular Property Prediction](https://aclanthology.org/2026.findings-emnlp.1796/) (Zhuang et al., Findings 2026)
ACL
- Jiaxi Zhuang, Yaorui Shi, Jue Hou, Mingwei Ye, Mingjun Xu, Yuming Su, Linfeng Zhang, Ying Qian, Linfeng Zhang, Guolin Ke, and Hengxing Cai. 2026. MppReasoner: Reasoning-Enhanced Large Language Models for Molecular Property Prediction. In Findings of the Association for Computational Linguistics: EMNLP 2026, pages 38399–38421, Budapest, Hungary. Association for Computational Linguistics.