ReqLens: An Interactive Evidence-Grounded Multi-Agent System for Document-to-Requirements Generation

Manojit Chakraborty, Pranav Laddhad, and Sagnik Ghosh presented ReqLens, an interactive multi-agent NLP system that turns mixed project documents into Software Requirements Specifications while linking each requirement to source evidence, at AACL-IJCNLP 2026 in Hengqin, China (pages 74–81). Evaluated on 13 projects against direct-generation and modular baselines plus component ablations, ReqLens achieved the strongest overall balance across unsupported-requirement rejection, valid-requirement retention, and seeded-defect filtering, with a formative study of four domain experts providing qualitative feedback on its interface and review workflow. The system ships with code, data, an installable package, and a narrated screencast.

ReqLens: An Interactive Evidence-Grounded Multi-Agent System for Document-to-Requirements Generation https://aclanthology.org/2026.aacl-demo.10.pdf Abstract Large language models can transform project documents into software requirements, but direct generation may introduce unsupported claims and hidden inconsistencies. We present ReqLens, an interactive multi-agent NLP system that extracts candidate requirements from mixed project documents, links them to source evidence, exposes graph-based dependencies and conflicts, and generates a Software Requirements Specification SRS through a human-in-the-loop workflow. We evaluate ReqLens on 13 projects using direct-generation and modular baselines, as well as component ablations. ReqLens achieves the strongest overall balance across unsupported-requirement rejection, valid-requirement retention, and seeded-defect filtering. A formative study with four domain experts provided qualitative feedback on the system’s interface and review workflow. ReqLens is accompanied by code, data, an installable package, and a narrated screencast. - Anthology ID: - 2026.aacl-demo.10 - Volume: - Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations https://aclanthology.org/volumes/2026.aacl-demo/ - Month: - November - Year: - 2026 - Address: - Hengqin, China - Editors: - Ningyu Zhang https://aclanthology.org/people/ningyu-zhang/ , Derry Wijaya https://aclanthology.org/people/derry-tanti-wijaya/ - Venues: - AACL https://aclanthology.org/venues/aacl/ | IJCNLP https://aclanthology.org/venues/ijcnlp/ - SIG: - Publisher: - Association for Computational Linguistics - Note: - Pages: - 74–81 - Language: - URL: - https://aclanthology.org/2026.aacl-demo.10/ https://aclanthology.org/2026.aacl-demo.10/ - DOI: - Cite ACL : - Manojit Chakraborty, Pranav Laddhad, and Sagnik Ghosh. 2026. ReqLens: An Interactive Evidence-Grounded Multi-Agent System for Document-to-Requirements Generation https://aclanthology.org/2026.aacl-demo.10/ . In Proceedings of the 15th International Joint Conference on Natural Language Processing and the 5th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics: System Demonstrations , pages 74–81, Hengqin, China. Association for Computational Linguistics. - Cite Informal : - ReqLens: An Interactive Evidence-Grounded Multi-Agent System for Document-to-Requirements Generation https://aclanthology.org/2026.aacl-demo.10/ Chakraborty et al., AACL-IJCNLP 2026 - PDF: - https://aclanthology.org/2026.aacl-demo.10.pdf https://aclanthology.org/2026.aacl-demo.10.pdf