@inproceedings{dhurve-etal-2026-decompose,
    title = "Decompose, Retrieve, Cite: A {RAG} Pipeline for Structured Report Generation from Technical Documentation",
    author = "Dhurve, Himanshu  and
      Panat, Sreedath  and
      Dandekar, Rajat  and
      Dandekar, Raj",
    editor = "Yang, Eugene  and
      Lawrie, Dawn  and
      MacAvaney, Sean  and
      Mayfield, James  and
      Soldaini, Luca  and
      Yates, Andrew",
    booktitle = "Proceedings of the 1st Workshop on Multilingual Report Generation via Retrieval Augmented Generation ({RAG}4{R}eports 2026)",
    month = jul,
    year = "2026",
    address = "San Diego, CA, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl-workshops/2026.rag4reports-1.4/",
    pages = "24--35",
    ISBN = "979-8-89176-417-0",
    abstract = "Retrieval-Augmented Generation (RAG) grounds language-model output in external knowledge, yet its application to dense technical documentation remains largely unexplored. Engineering software manuals pose compounding challenges: formulae are corrupted during PDF extraction, heterogeneous content types require different parsing treatment, and queries demand cross-document synthesis across multiple reference volumes.We present an end-to-end RAG system for OpenFOAM, an open-source computational fluid dynamics toolkit, operating in two modes. In single-query mode, a formula-preserving parser (Marker), adaptive header-aware chunking, two-stage dense-then-rerank retrieval, and a citation-enforcement prompt produce grounded, source-attributed answers across a 20-question benchmark.In report mode, a user prompt is decomposed into sub-questions via LLM planning; each sub-question undergoes independent retrieval and cross-encoder re-ranking, and the deduplicated chunk set is passed to a long-context generation call that produces a structured, multi-section report with inline citations.Evaluated on a 10-prompt golden set with a six-dimension LLM-as-a-judge framework, both pipelines achieve overall scores above 4.6/5.0 with perfect citation correctness (5.0/5.0). The decomposed pipeline demonstrates superior robustness (90{\%} vs 70{\%} judge success rate). Retrieval analysis using page-level ground truth reveals low absolute recall ({\ensuremath{<}}14{\%}), identifying retrieval breadth as the primary bottleneck."
}