← All Publications

ReqGenX: An Empirical Study of Atomic Decomposition, Artifact Regeneration, and Reconstruction for Legacy SRS Documents

Ragib Shahariar Ayon, Rayed Fahmi, Sumon Biswas, Shibbir Ahmed

ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM) 2026

Abstract

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. We study whether legacy SRS documents can be transformed into traceable synthetic pre-SRS artifacts that support fine-grained evaluation of LLM-based SRS generation. 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 under constrained prompting, enabling reconstruction of specifications that can be traced back to their originating requirements.

BibTeX

@inproceedings{ayon2026reqgenx, title={ReqGenX: An Empirical Study of Atomic Decomposition, Artifact Regeneration, and Reconstruction for Legacy SRS Documents}, author={Ayon, Ragib Shahariar and Fahmi, Rayed and Biswas, Sumon and Ahmed, Shibbir}, booktitle={Proceedings of the ACM/IEEE International Symposium on Empirical Software Engineering and Measurement (ESEM)}, year={2026} }