back to home

June 26 2026

How Generation Architecture Shapes Code Complexity in Multi-Agent LLM Systems

LLM code generation has moved from single-shot prompting to multi-agent orchestrations — analyst, coder, tester, and debugger pipelines. These systems are almost always judged on functional correctness (pass@1). But the code they produce is also read, reviewed, debugged, and maintained by humans, and that structural complexity carries a downstream cost that pass@1 never captures.

This preprint asks a question the field has largely left open: does the choice of generation architecture change the structural complexity of the code, and if so, which orchestration layers carry the cost?

Setup

Key findings

Why it matters for practitioners

This is a preprint and is not published in a venue — it serves as an open archival record.