Agentic genomics: From pipeline automation to autonomous validation

This is the authors' abstract. We don't add key points for this paper.

Genomics has entered a phase in which AI agents can autonomously discover, configure, execute, and chain bioinformatics operations from natural-language instructions. We term this paradigm "agentic genomics": the delegation of multi-step genomic analyses to autonomous software agents that select tools, manage dependencies, and adapt execution in response to intermediate results, mediated by large language models (LLMs) and constrained by domain-specific skill libraries. We argue that agentic genomics shifts the bottleneck in computational biology from pipeline construction to validation. We examine emerging systems, including CellAtria, AutoBA, Bio-Copilot, and ClawBio, and assess their divergent architectures. We propose a tiered validation framework spanning research-grade, benchmarked, and clinical-grade analyses and argue that equity-aware design must be a systems requirement rather than an optional aspiration. We identify the infrastructure needed to make agentic genomics trustworthy.