aiqbench analysis
This research demonstrates a practical application of agentic AI in software engineering, where a multi-agent framework autonomously reverse-engineers undocumented enterprise systems into structured business requirements. By leveraging static analysis and execution traces, the system reduces migration timelines from years to minutes while validating extracted rules against real production defects. This marks a significant shift from manual knowledge extraction to automated cognitive modeling for large-scale legacy system modernization.
From Code to Requirements: Agentic Reverse Engineering of Business Rules at Enterprise Scale
arXiv:2609.22719v1 Announce Type: cross Abstract: Business requirements for enterprise software systems are rarely captured in structured form; the logic resides instead in source code, configuration files, and institutional memory. When these systems must be migrated, extended, or audited, the absence of formal requirements artifacts forces teams into expensive, knowledge-losing manual reverse engineering. This paper presents an agentic framework that autonomously generates Business Requirements Documents (bRDs) through reverse engineering of undocumented enterprise software. Seven specialized agents collaborate to discover user journeys, extract business rules, and synthesize a locked bRD from code, test suites, configuration, and available documentation, supported by static analysis tools, guided by embedded expert practitioner cognitive models, and overseen by human reviewers at controlled escalation points. Measured on actual execution traces across a real enterprise deployment, the framework generates comprehensive bRDs in under nine minutes per service, with extracted rules independently corroborated against real production defect records. In a comparable prior migration to the same target architecture, delivery required over two years; on the present programme the framework achieves a cost reduction exceeding 98% against a baseline derived from actual repository metrics using IFPUG complexity models and industry benchmark labor rates.
Abstract:Business requirements for enterprise software systems are rarely captured in structured form; the logic resides instead in source code, configuration files, and institutional memory. When these systems must be migrated, extended, or audited, the absence of formal requirements artifacts forces teams into expensive, knowledge-losing manual reverse engineering. This paper presents an agentic framework that autonomously generates Business Requirements Documents (bRDs) through reverse engineering of undocumented enterprise software. Seven specialized agents collaborate to discover user journeys, extract business rules, and synthesize a locked bRD from code, test suites, configuration, and available documentation, supported by static analysis tools, guided by embedded expert practitioner cognitive models, and overseen by human reviewers at controlled escalation points. Measured on actual execution traces across a real enterprise deployment, the framework generates comprehensive bRDs in under nine minutes per service, with extracted rules independently corroborated against real production defect records. In a comparable prior migration to the same target architecture, delivery required over two years; on the present programme the framework achieves a cost reduction exceeding 98% against a baseline derived from actual repository metrics using IFPUG complexity models and industry benchmark labor rates.
Software Engineering (cs.SE); Artificial Intelligence (cs.AI)
arXiv:2609.22719 [cs.SE]
(or arXiv:2609.22719v1 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2609.22719 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Full text under the publisher's open licence · 284 words
Related coverage

[AINews] Meta Muse Wonder & Wonder Full: MSL’s Claude 5.5-tier Frontier Model
Latent Space · Oct 13, 2026

Promptimus: Improving already good LLM prompts with zero manual engineering
Amazon Science · May 14, 2026

Brief independent investigation of agents’ behavior, reasoning and collaboration in the OpenAI / Hugging Face hacking incident
METR · Aug 26, 2026

Vertical Advantage: Transforming Industries with Lakebase and Agentic AI
Databricks · Aug 27, 2026