StructAgent: Orchestrating Cryo-EM Model Building and Refinement with a Multi-Agent LLM System

Building and refining cryo-EM atomic models often requires long, project-specific workflows that combine map inspection, prior structural knowledge, restraints, refinement, validation and expert review. Existing programs perform many individual operations, but coordinating them across iterative model-building sessions remains manual and difficult to audit. We present StructAgent, a user-guided multi-agent resource for cryo-EM model building and refinement. StructAgent couples a domain agent for literature-grounded structural reasoning with an execution agent that runs local software, tracks state, recovers from failures and records provenance. Expert approval gates control major model-changing actions. In three case studies, StructAgent refitted a 64-chain proteasome from an earlier template, audited 530 ribosomal metal-ion sites and guided a chemically ambiguous ligand fit in a folate-metabolism enzyme from ongoing work. These demonstrations show that agentic orchestration can convert modeling intent into auditable, reviewable software workflows while preserving expert control and final scientific judgment.