ARCHER: Agentic Rule and Compliance Harness for Executable Regulations

2026-07-28

AI Summary

This study addresses the limitations of existing automated tools for building code compliance verification, which suffer from poor generalizability, lack of transparency, and limited scalability due to their reliance on manual comparison between regulatory texts and BIM models. To overcome these challenges, this work proposes a test-driven, deterministically orchestrated multi-agent program synthesis framework that introduces a novel deterministic multi-agent collaboration mechanism to automatically translate regulatory texts into executable, auditable compliance-checking code. The approach integrates hierarchical rule parsing, large language models—including both closed-source APIs and open-source local models—and test-driven development within a multi-tiered data governance evaluation framework. Experimental results demonstrate that the proposed method achieves the highest accuracy across all backbone models, improving average joint accuracy by 82% over baselines; notably, open-source local models attain 97.8% of the performance of state-of-the-art APIs at only one-quarter of the cost.

Abstract

Verifying building compliance requires validating thousands of rules against large Building Information Modeling (BIM) designs, which is laborious, capital-intensive, and unscalable. Existing Automated Compliance Checkers (ACCs) are often difficult to generalize across different scenarios, as they are typically developed for highly specific rule sets and use cases. In addition, many ACCs are proprietary, meaning the underlying verification code is not released to end users, so users cannot verify whether their regulatory intent can be accurately captured. We introduce ARCHER (Agentic Rule and Compliance Harness for Executable Regulations), a test-driven, deterministically orchestrated multi-agent program-synthesis harness that generates auditable verification code from regulatory Codes of Practice, enabling transparent, adaptable, and scalable compliance checking. To characterize what makes agentic synthesis work, we evaluate a taxonomy of six harnesses of increasing agentic sophistication across four backbone models, spanning realistic data-governance tiers (from frontier third-party APIs to a fully on-premise open-weights model) on a novel dataset derived from real-world compliance scenarios. ARCHER's deterministic multi-agent orchestration achieves the highest accuracy for every backbone, improving mean union accuracy by 82% over a naive single-pass prompting baseline. Our cost-accuracy analysis further shows that using the ARCHER harness, a self-hosted open-weights model can reach 97.8% of frontier-API accuracy at a quarter of the cost, making data-sovereign compliance checking practical.

Problem

• building compliance
• Automated Compliance Checkers
• regulatory verification
• BIM
• executable regulations

Innovation

• multi-agent program synthesis
• executable regulations
• deterministic orchestration
• automated compliance checking
• auditable code generation