@inproceedings{liu-etal-2026-genomas,
title = "{G}eno{MAS}: Guided Multi-Agent Programming for Scientific Discovery from Genomic Data",
author = "Liu, Haoyang and
Li, Yijiang and
Wang, Haohan",
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.1395/",
pages = "29695--29738",
ISBN = "979-8-89176-462-0",
abstract = "Gene expression analysis holds the key to many biomedical discoveries, yet extracting insights from raw transcriptomic data remains challenging due to the complexity of multiple large, semi-structured files and the need for extensive domain expertise. Current approaches either rely on inflexible workflows that fail in edge cases or fully autonomous agents that lack the precision required for rigorous scientific inquiry. GenoMAS addresses this by presenting a team of LLM-based agents that integrates structured workflows with autonomous adaptability, orchestrating diverse specialized agents through typed message-passing protocols. At its core lies a guided-planning framework where programming agents decompose task guidelines into Action Units and dynamically choose to advance, revise, bypass, or backtrack, maintaining logical coherence while adapting to the idiosyncrasies of genomic data. On the GenoTEX benchmark, GenoMAS achieves 89.13{\%} CSC for preprocessing and 60.48{\%} F{\ensuremath{_1}} for identifying trait-associated genes, surpassing prior art by 10.61{\%} and 16.85{\%}. It again outperforms strong agent baselines on ScienceAgentBench and DiscoveryBench, two independent bioinformatics benchmarks beyond transcriptomics. Its analyses yield gene-phenotype associations that are biologically plausible and corroborated by the literature. Our code is available at https://github.com/Liu-Hy/GenoMAS."
}<?xml version="1.0" encoding="UTF-8"?>
<modsCollection xmlns="http://www.loc.gov/mods/v3">
<mods ID="liu-etal-2026-genomas">
<titleInfo>
<title>GenoMAS: Guided Multi-Agent Programming for Scientific Discovery from Genomic Data</title>
</titleInfo>
<name type="personal">
<namePart type="given">Haoyang</namePart>
<namePart type="family">Liu</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Yijiang</namePart>
<namePart type="family">Li</namePart>
<role>
<roleTerm authority="marcrelator" type="text">author</roleTerm>
</role>
</name>
<name type="personal">
<namePart type="given">Haohan</namePart>
<namePart type="family">Wang</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>Gene expression analysis holds the key to many biomedical discoveries, yet extracting insights from raw transcriptomic data remains challenging due to the complexity of multiple large, semi-structured files and the need for extensive domain expertise. Current approaches either rely on inflexible workflows that fail in edge cases or fully autonomous agents that lack the precision required for rigorous scientific inquiry. GenoMAS addresses this by presenting a team of LLM-based agents that integrates structured workflows with autonomous adaptability, orchestrating diverse specialized agents through typed message-passing protocols. At its core lies a guided-planning framework where programming agents decompose task guidelines into Action Units and dynamically choose to advance, revise, bypass, or backtrack, maintaining logical coherence while adapting to the idiosyncrasies of genomic data. On the GenoTEX benchmark, GenoMAS achieves 89.13% CSC for preprocessing and 60.48% F\ensuremath₁ for identifying trait-associated genes, surpassing prior art by 10.61% and 16.85%. It again outperforms strong agent baselines on ScienceAgentBench and DiscoveryBench, two independent bioinformatics benchmarks beyond transcriptomics. Its analyses yield gene-phenotype associations that are biologically plausible and corroborated by the literature. Our code is available at https://github.com/Liu-Hy/GenoMAS.</abstract>
<identifier type="citekey">liu-etal-2026-genomas</identifier>
<location>
<url>https://aclanthology.org/2026.findings-emnlp.1395/</url>
</location>
<part>
<date>2026-10</date>
<extent unit="page">
<start>29695</start>
<end>29738</end>
</extent>
</part>
</mods>
</modsCollection>
%0 Conference Proceedings
%T GenoMAS: Guided Multi-Agent Programming for Scientific Discovery from Genomic Data
%A Liu, Haoyang
%A Li, Yijiang
%A Wang, Haohan
%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 liu-etal-2026-genomas
%X Gene expression analysis holds the key to many biomedical discoveries, yet extracting insights from raw transcriptomic data remains challenging due to the complexity of multiple large, semi-structured files and the need for extensive domain expertise. Current approaches either rely on inflexible workflows that fail in edge cases or fully autonomous agents that lack the precision required for rigorous scientific inquiry. GenoMAS addresses this by presenting a team of LLM-based agents that integrates structured workflows with autonomous adaptability, orchestrating diverse specialized agents through typed message-passing protocols. At its core lies a guided-planning framework where programming agents decompose task guidelines into Action Units and dynamically choose to advance, revise, bypass, or backtrack, maintaining logical coherence while adapting to the idiosyncrasies of genomic data. On the GenoTEX benchmark, GenoMAS achieves 89.13% CSC for preprocessing and 60.48% F\ensuremath₁ for identifying trait-associated genes, surpassing prior art by 10.61% and 16.85%. It again outperforms strong agent baselines on ScienceAgentBench and DiscoveryBench, two independent bioinformatics benchmarks beyond transcriptomics. Its analyses yield gene-phenotype associations that are biologically plausible and corroborated by the literature. Our code is available at https://github.com/Liu-Hy/GenoMAS.
%U https://aclanthology.org/2026.findings-emnlp.1395/
%P 29695-29738
Markdown (Informal)
[GenoMAS: Guided Multi-Agent Programming for Scientific Discovery from Genomic Data](https://aclanthology.org/2026.findings-emnlp.1395/) (Liu et al., Findings 2026)
ACL