{"slug": "reqlens-an-interactive-evidence-grounded-multi-agent-system-for-document-to", "title": "ReqLens: An Interactive Evidence-Grounded Multi-Agent System for Document-to-Requirements Generation", "summary": "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.", "body_md": "## [ReqLens: An Interactive Evidence-Grounded Multi-Agent System for Document-to-Requirements Generation](https://aclanthology.org/2026.aacl-demo.10.pdf)\n\n##### Abstract\n\nLarge 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.\n- Anthology ID:\n- 2026.aacl-demo.10\n- Volume:\n- [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/)\n- Month:\n- November\n- Year:\n- 2026\n- Address:\n- Hengqin, China\n- Editors:\n- [Ningyu Zhang](https://aclanthology.org/people/ningyu-zhang/) ,[Derry Wijaya](https://aclanthology.org/people/derry-tanti-wijaya/)\n- Venues:\n- [AACL](https://aclanthology.org/venues/aacl/) |[IJCNLP](https://aclanthology.org/venues/ijcnlp/)\n- SIG:\n- Publisher:\n- Association for Computational Linguistics\n- Note:\n- Pages:\n- 74–81\n- Language:\n- URL:\n- [https://aclanthology.org/2026.aacl-demo.10/](https://aclanthology.org/2026.aacl-demo.10/)\n- DOI:\n- Cite (ACL):\n- 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.\n- Cite (Informal):\n- [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)\n- PDF:\n- [https://aclanthology.org/2026.aacl-demo.10.pdf](https://aclanthology.org/2026.aacl-demo.10.pdf)", "url": "https://wpnews.pro/news/reqlens-an-interactive-evidence-grounded-multi-agent-system-for-document-to", "canonical_source": "https://aclanthology.org/2026.aacl-demo.10/", "published_at": "2026-11-02 00:00:00+00:00", "updated_at": "2026-11-06 11:21:43.602576+00:00", "lang": "en", "topics": ["natural-language-processing", "large-language-models", "ai-agents", "ai-research", "ai-tools"], "entities": ["ReqLens", "Manojit Chakraborty", "Pranav Laddhad", "Sagnik Ghosh", "AACL-IJCNLP 2026", "Association for Computational Linguistics"], "also_reported_by": [], "alternates": {"html": "https://wpnews.pro/news/reqlens-an-interactive-evidence-grounded-multi-agent-system-for-document-to", "markdown": "https://wpnews.pro/news/reqlens-an-interactive-evidence-grounded-multi-agent-system-for-document-to.md", "text": "https://wpnews.pro/news/reqlens-an-interactive-evidence-grounded-multi-agent-system-for-document-to.txt", "jsonld": "https://wpnews.pro/news/reqlens-an-interactive-evidence-grounded-multi-agent-system-for-document-to.jsonld"}}