# GenoMAS introduces LLM‑driven agents for genomic data analysis

> The system, described in an arXiv paper on Oct 21 2026, claims higher accuracy on benchmark gene‑expression tasks.

Oossa · 2026-10-21 · https://oossa.com/en/genomas-introduces-llm-driven-agents-for-genomic-data-analysis

Researchers led by Haoyang Liu released GenoMAS, a team of language‑model agents that work together to clean and interpret transcriptomic data. The agents follow a guided‑planning framework that lets them break tasks into small actions and adjust their steps when data are messy. On the GenoTEX benchmark, GenoMAS reached 89.13% correctness for preprocessing and an F1 score of 60.48% for finding trait‑linked genes, beating previous methods by 10.61% and 16.85% respectively.

## The facts

- Paper posted on arXiv on 2026-10-21
- GenoMAS scored 89.13% CSC and 60.48% F1 on GenoTEX

## Why it matters

If the reported gains hold, biologists could rely on fewer manual steps to discover gene‑phenotype links.

## Sources & references

1. [GenoMAS: Guided Multi-Agent Programming for Scientific Discovery from Genomic Data](https://arxiv.org/abs/2507.21035) – arXiv cs.MA, 2026-10-21

Last updated: 2026-10-21