ReqGenX: An Empirical Study of Atomic Decomposition, Artifact Regeneration, and Reconstruction for Legacy SRS Documents
Software EngineeringArtificial Intelligence
Summary
The authors studied how to break down old software requirement documents into smaller, traceable pieces to better evaluate AI-generated new requirement documents. They created a tool called ReqGenX that splits these documents into clear, source-based atomic statements and organizes them into standard artifact types using multiple AI models. Their experiments showed that these smaller pieces and the generated artifacts closely matched the original content, allowing detailed checks of quality and information preservation. This approach helps reveal trade-offs between how faithful, complete, and informative the AI-generated documents are.
Authors
Ragib Shahariar Ayon, Rayed Fahmi, Sumon Biswas, Shibbir Ahmed
Abstract
Background: Evaluating automated Software Requirements Specification (SRS) generation is challenging because few datasets provide fine-grained traceability between source requirements, intermediate elicitation artifacts, and generated specifications. Aims: We aim to study whether legacy SRS documents can be transformed into traceable synthetic pre-SRS artifacts that support fine-grained evaluation of LLM-based SRS generation. Method: We conduct an empirical study using ReqGenX, a controlled pipeline that decomposes SRS sections into source-grounded atomic statements, routes atoms to standards-inspired artifact types through multi-LLM plurality voting, and generates artifacts using constrained prompts with iterative judge-guided refinement. We evaluate ReqGenX on seven PURE SRS documents using grounding, quality, information retention, and downstream reconstruction analyses. Results: ReqGenX produces faithful and usable atoms, with median AlignScore values typically between 0.96 and 0.99 and Prometheus scores ranging from 4.34 to 4.85. Generated artifacts remain strongly grounded in their source atoms, with AlignScore values typically between 0.80--0.94 and judge pass rates near 100%; stricter Prometheus evaluation yields pass rates from 54.8% to 97.1%. In a downstream SRS reconstruction case study, artifact-backed atoms remain recoverable from generated SRSs, with SBERT means between 0.69 and 0.75 and AlignScore medians between 0.76 and 0.84. Conclusions: Traceable synthetic pre-SRS artifacts can support more fine-grained evaluation of LLM-based SRS generation, while exposing tradeoffs among faithfulness, information retention, and artifact completeness.