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% F₁ 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.