GenoMAS: Guided Multi-Agent Programming for Scientific Discovery from Genomic Data

Beyond transcriptomics, it outperforms strong agent baselines on ScienceAgentBench and DiscoveryBench, two independent bioinformatics benchmarks. It comes from a paper posted to arXiv on 21 October 2026. 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 data preprocessing and 60.48% $F_1$ for identifying trait-associated genes, surpassing prior art by 10.61% and 16.85%. Qualitative analysis shows that GenoMAS identifies gene-phenotype associations that are biologically plausible and corroborated by the literature.

Why it counts

Beyond transcriptomics, it outperforms strong agent baselines on ScienceAgentBench and DiscoveryBench, two independent bioinformatics benchmarks.

Sources

Primary source: primary source

What is not known

This brief does not claim independent replication. Claims that appear only on X and not in the primary source stay unknown.