ArXiv: Architecture Descriptors Cut AI Coding Agent Navigation by 33-44% — 7,012 Claude Code Sessions Analyzed

arXiv·high signalXBlueskyLinkedInCopy link

Paper arXiv:2604.13108 demonstrates that formal architecture descriptors (structured documents declaring module boundaries, symbol signatures, and data flows) reduce AI coding agent navigation steps by 33-44% (Wilcoxon p=0.009, Cohen's d=0.92). An observational study across 7,012 Claude Code sessions shows 52% reduction in agent behavioral variance. Proposes intent.lisp: an S-expression format where projects declare architecture for agent consumption. Automatically generated descriptors achieve 100% accuracy vs 80% blind.