# Formal Architecture Descriptors as Navigation Primitives for AI Coding Agents

arXiv: https://arxiv.org/abs/2604.13108 · HTML: https://mlsanity.com/paper/2604.13108/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 8 of its 18 references that are in the map.
- First posted on arXiv 11 Apr 2026.

## Placed in

- LLM agents and tool use / [Software engineering coding agents](https://mlsanity.com/agents/software-engineering-coding-agents/)

## Builds on (most cited first, 8 of 8)

- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [RepoGraph: Enhancing AI Software Engineering with Repository-level Code Graph](https://mlsanity.com/paper/2410.14684/) (2024)
- [Effective Strategies for Asynchronous Software Engineering Agents](https://mlsanity.com/paper/2603.21489/) (2026)
- [CodeCRDT: Observation-Driven Coordination for Multi-Agent LLM Code Generation](https://mlsanity.com/paper/2510.18893/) (2025)
- [Codified Context: Infrastructure for AI Agents in a Complex Codebase](https://mlsanity.com/paper/2602.20478/) (2026)
- [Architecture Without Architects: How AI Coding Agents Shape Software Architecture](https://mlsanity.com/paper/2604.04990/) (2026)

## Abstract (arXiv)

AI coding agents spend a substantial fraction of their tool calls on undirected codebase exploration. We investigate whether providing agents with formal architecture descriptors can reduce this navigational overhead. We present three complementary studies. First, a controlled experiment (24 code localization tasks x 4 conditions, Claude Sonnet 4.6, temperature=0) demonstrates that architecture context reduces navigation steps by 33-44% (Wilcoxon p=0.009, Cohen's d=0.92), with no significant format difference detected across S-expression, JSON, YAML, and Markdown. Second, an artifact-vs-process experiment (15 tasks x 3 conditions) demonstrates that an automatically generated descriptor achieves 100% accuracy versus 80% blind (p=0.002, d=1.04), proving direct navigational value independent of developer self-clarification. Third, an observational field study across 7,012 Claude Code sessions shows 52% reduction in agent behavioral variance. A writer-side experiment (96 generation runs, 96 error injections) reveals critical failure mode differences: JSON fails atomically, YAML silently corrupts 50% of errors, S-expressions detect all structural completeness errors. We propose intent.lisp, an S-expression architecture descriptor, and open-source the Forge toolkit.