@inproceedings{fan-etal-2026-cmas,
title = "{CMAS}: Enhancing Data Augmentation for Molecular Graph Classification via a Collaborative Multi-Agent System",
author = "Fan, Xuanting and
Wang, Chenyu and
Liu, Xin and
Ren, Weiyi and
Wang, Yifan and
Luo, Xiao",
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.2300/",
pages = "49310--49328",
ISBN = "979-8-89176-462-0",
abstract = "Data augmentation is widely adopted in molecular graph learning due to its practical benefits in enhancing model performance. However, conventional augmentation like edge deletion often destroys critical chemical semantics, as molecular properties are highly sensitive to structural changes. To address this, we introduce CMAS, a novel $\underline{\mathrm{C}}$ollaborative $\underline{\mathrm{M}}$ulti-$\underline{\mathrm{A}}$gent $\underline{\mathrm{S}}$ystem for enhancing data augmentation in molecular graph classification. Specifically, for each input molecule, we first use a BRICS-based decomposition strategy with prompt-guided LLM generation to produce structurally diverse candidates while preserving the core scaffold. To ensure that the generated candidates preserve the physicochemical properties of the original molecule, we retrieve domain-specific chemical knowledge from a knowledge graph and prompt an LLM to assess property consistency, effectively filtering out semantically divergent samples. Finally, we perform rule-based sanitization with iterative feedback to ensure chemical validity and preserve distributional diversity, resulting in a high-quality augmented molecular set. Extensive experiments on MoleculeNet benchmarks validate the superiority of CMAS against several state-of-the-art baselines. Code is available at https://github.com/Catfromuibe/CMAS."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="fan-etal-2026-cmas">
<titleInfo>
<title>CMAS: Enhancing Data Augmentation for Molecular Graph Classification via a Collaborative Multi-Agent System</title>
</titleInfo>
<name type="personal">
<namePart type="given">Xuanting</namePart>
<namePart type="family">Fan</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Chenyu</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xin</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Weiyi</namePart>
<namePart type="family">Ren</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yifan</namePart>
<namePart type="family">Wang</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Xiao</namePart>
<namePart type="family">Luo</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>Data augmentation is widely adopted in molecular graph learning due to its practical benefits in enhancing model performance. However, conventional augmentation like edge deletion often destroys critical chemical semantics, as molecular properties are highly sensitive to structural changes. To address this, we introduce CMAS, a novel \underlineCollaborative \underlineMulti-\underlineAgent \underlineSystem for enhancing data augmentation in molecular graph classification. Specifically, for each input molecule, we first use a BRICS-based decomposition strategy with prompt-guided LLM generation to produce structurally diverse candidates while preserving the core scaffold. To ensure that the generated candidates preserve the physicochemical properties of the original molecule, we retrieve domain-specific chemical knowledge from a knowledge graph and prompt an LLM to assess property consistency, effectively filtering out semantically divergent samples. Finally, we perform rule-based sanitization with iterative feedback to ensure chemical validity and preserve distributional diversity, resulting in a high-quality augmented molecular set. Extensive experiments on MoleculeNet benchmarks validate the superiority of CMAS against several state-of-the-art baselines. Code is available at https://github.com/Catfromuibe/CMAS.</abstract>
<identifier type="citekey">fan-etal-2026-cmas</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.2300/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>49310</start>
<end>49328</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T CMAS: Enhancing Data Augmentation for Molecular Graph Classification via a Collaborative Multi-Agent System
%A Fan, Xuanting
%A Wang, Chenyu
%A Liu, Xin
%A Ren, Weiyi
%A Wang, Yifan
%A Luo, Xiao
%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 fan-etal-2026-cmas
%X Data augmentation is widely adopted in molecular graph learning due to its practical benefits in enhancing model performance. However, conventional augmentation like edge deletion often destroys critical chemical semantics, as molecular properties are highly sensitive to structural changes. To address this, we introduce CMAS, a novel \underlineCollaborative \underlineMulti-\underlineAgent \underlineSystem for enhancing data augmentation in molecular graph classification. Specifically, for each input molecule, we first use a BRICS-based decomposition strategy with prompt-guided LLM generation to produce structurally diverse candidates while preserving the core scaffold. To ensure that the generated candidates preserve the physicochemical properties of the original molecule, we retrieve domain-specific chemical knowledge from a knowledge graph and prompt an LLM to assess property consistency, effectively filtering out semantically divergent samples. Finally, we perform rule-based sanitization with iterative feedback to ensure chemical validity and preserve distributional diversity, resulting in a high-quality augmented molecular set. Extensive experiments on MoleculeNet benchmarks validate the superiority of CMAS against several state-of-the-art baselines. Code is available at https://github.com/Catfromuibe/CMAS.
%U https://aclanthology.org/2026.findings-emnlp.2300/
%P 49310-49328
Markdown (Informal)
[CMAS: Enhancing Data Augmentation for Molecular Graph Classification via a Collaborative Multi-Agent System](https://aclanthology.org/2026.findings-emnlp.2300/) (Fan et al., Findings 2026)
ACL