# Architecture as Capability Equalizer for Coding Agents

arXiv: https://arxiv.org/abs/2608.21747 · HTML: https://mlsanity.com/paper/2608.21747/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Software engineering coding agents, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 28 references that are in the map.
- First posted on arXiv 22 Aug 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, 13 of 13)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Evaluating Large Language Models Trained on Code](https://mlsanity.com/paper/2107.03374/) (2021)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Self-planning Code Generation with Large Language Models](https://mlsanity.com/paper/2303.06689/) (2023)
- [BaxBench: Can LLMs Generate Correct and Secure Backends?](https://mlsanity.com/paper/2502.11844/) (2025)
- [Constraint Decay: The Fragility of LLM Agents in Backend Code Generation](https://mlsanity.com/paper/2605.06445/) (2026)
- [Evaluating Software Process Models for Multi-Agent Class-Level Code Generation](https://mlsanity.com/paper/2511.09794/) (2025)
- [Architecture Without Architects: How AI Coding Agents Shape Software Architecture](https://mlsanity.com/paper/2604.04990/) (2026)
- [CodeSpec: Dual Executable Specifications for Agentic Long-Horizon Feature Development](https://mlsanity.com/paper/2607.26777/) (2026)
- [ConCodeEval: Evaluating Large Language Models for Code Constraints in Domain-Specific Languages](https://mlsanity.com/paper/2407.03387/) (2024)
- [Beyond Correctness: Enhancing Architectural Reasoning in Code LLMs via Scalable Labeling with Agentic Judgment](https://mlsanity.com/paper/2606.14948/) (2026)

## Built on by (most cited first, 1 of 1)

- [The Answer Path and the Grounding Instruction in LLM Question Answering over Knowledge Graphs](https://mlsanity.com/paper/2609.10237/) (2026)

## Abstract (arXiv)

LLM-based coding agents generate complete software systems from high-level descriptions, yet little is known about how the format of architecture specifications affects the quality of generated code or whether this effect depends on model capability. We present a controlled experiment comparing five informationally equivalent specification formats (informal prose, Mermaid diagrams with constraints and ADRs, OpenAPI, C4/Structurizr DSL, and TypeScript interface contracts with ArchUnit-style rules) across six models from three vendor families (Anthropic Claude, OpenAI GPT, Google Gemini). Across 90 multi-turn agent trials, specification format shows a strong format x model interaction. On the strongest models (Sonnet 4.6, GPT-5), format barely matters (quality spread 0.17-0.92). On weaker models, format produces spreads of 0.83-2.42 points, with code-proximate formats (OpenAPI, TypeScript contracts) recovering most of the capability gap. Mid-tier models can consume more tokens than frontier models for worse output when they enter compilation debugging loops that stronger models avoid. Self-validation rates collapse from 100% (Sonnet) to 0% (Gemini Flash) across the capability spectrum. TypeScript contracts triple API route coverage for the weakest model (33% to 100%). Structured architecture specifications serve as a capability equalizer, with value inversely proportional to model strength and the largest returns for cost-optimized deployments.