# Reversa: A Reverse Documentation Engineering Framework for Converting Legacy Software into Operational Specifications for AI Agents

arXiv: https://arxiv.org/abs/2605.18684 · HTML: https://mlsanity.com/paper/2605.18684/

## 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 19 of its 39 references that are in the map.
- First posted on arXiv 18 May 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, 19 of 19)

- [Program Synthesis with Large Language Models](https://mlsanity.com/paper/2108.07732/) (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)
- [ChatDev: Communicative Agents for Software Development](https://mlsanity.com/paper/2307.07924/) (2023)
- [Large Language Models for Software Engineering: A Systematic Literature Review](https://mlsanity.com/paper/2308.10620/) (2023)
- [Large Language Model-Based Agents for Software Engineering: A Survey](https://mlsanity.com/paper/2409.02977/) (2024)
- [RepoAgent: An LLM-Powered Open-Source Framework for Repository-level Code Documentation Generation](https://mlsanity.com/paper/2402.16667/) (2024)
- [Learning From Failure: Integrating Negative Examples when Fine-tuning Large Language Models as Agents](https://mlsanity.com/paper/2402.11651/) (2024)
- [Advancing Requirements Engineering through Generative AI: Assessing the Role of LLMs](https://mlsanity.com/paper/2310.13976/) (2023)
- [Using LLMs in Software Requirements Specifications: An Empirical Evaluation](https://mlsanity.com/paper/2404.17842/) (2024)
- [How Effective are Large Language Models in Generating Software Specifications?](https://mlsanity.com/paper/2306.03324/) (2023)
- [Hierarchical Repository-Level Code Summarization for Business Applications Using Local LLMs](https://mlsanity.com/paper/2501.07857/) (2025)
- [Software Architecture in Practice: Challenges and Opportunities](https://mlsanity.com/paper/2308.09978/) (2023)
- [Testing the Effect of Code Documentation on Large Language Model Code Understanding](https://mlsanity.com/paper/2404.03114/) (2024)
- [Knowledge Graph Based Repository-Level Code Generation](https://mlsanity.com/paper/2505.14394/) (2025)
- [AutoReSpec: A Framework for Generating Specification using Large Language Models](https://mlsanity.com/paper/2604.03758/) (2026)
- [ReqInOne: A Large Language Model-Based Agent for Software Requirements Specification Generation](https://mlsanity.com/paper/2508.09648/) (2025)
- [Leveraging Large Language Models for Use Case Model Generation from Software Requirements](https://mlsanity.com/paper/2511.09231/) (2025)
- [Reproducible, Explainable, and Effective Evaluations of Agentic AI for Software Engineering](https://mlsanity.com/paper/2604.01437/) (2026)

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

- [From Prompt to Process: a Process Taxonomy and Comparative Assessment of Frameworks Supporting AI Software Development Agents](https://mlsanity.com/paper/2606.04967/) (2026)

## Abstract (arXiv)

Legacy systems concentrate business rules, architectural decisions, and operational exceptions that often remain implicit in code, data, configuration, and maintenance practices. At the same time, language-model-based coding agents depend on reliable context, correctness criteria, and behavioral contracts to modify real systems with lower risk. This paper presents Reversa, a reverse documentation engineering framework for converting legacy software into traceable operational specifications for AI agents. Reversa organizes this process as a multi-agent pipeline: specialized agents map the project surface, analyze modules, extract implicit rules, synthesize architecture, write unit-level specifications, and review generated claims. The proposal emphasizes three mechanisms: traceability between code and specification, explicit confidence marking, and preservation of gaps for human validation. The framework is distributed as a Node.js CLI, installs skills across multiple agent engines, and uses a SHA-256 manifest to preserve modified files during update or uninstall operations. In addition to the architectural description, we report an exploratory case study on migrating an ATM from COBOL to Go, in which the pipeline produced 517 claims classified by an internal confidence index, 10 registered gaps, 53 Gherkin parity scenarios, and a reconstruction plan with 9 of 11 tasks completed at inventory time. Final parity validation and cutover were not completed in this study. We do not claim broad empirical superiority; we position the contribution with respect to the literature on reverse engineering, LLM-based documentation, and software agents, and propose an evaluation protocol with metrics for coverage, traceability, confidence, utility, and cost.