Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints

[2608.15032] Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science > Computation and Language arXiv:2608.15032 (cs) [Submitted on 15 Aug 2026] Title: Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints Authors: Bruno Chicelli , Henrique Alves , Rodrigo Anselmo , Joshua Weinberg , Felipe Lemos , Jan Baryla View a PDF of the paper titled Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints, by Bruno Chicelli and 5 other authors View PDF HTML (experimental) Abstract: Converting a set of architectural blueprints into a complete material quantity takeoff requires visual perception across drawing sheets, dimensional and multi-hop reasoning, and grounding in construction conventions that the drawings never state. We present Handoff-H1, a takeoff system built from three layers: purpose-built computer-vision models that extract primitives; tool-using agents equipped with image operations and in-house visual-task tools, including CV-model-backed counting, detection and plan decomposition; and a persistent, hierarchically structured project foundation, grounded in a curated construction knowledge base. We evaluate on the Construction Blueprint Takeoff Benchmark: 10 real residential blueprint sets paired with consensus-validated expert takeoffs - 2,009 verified line items, restricted for scoring to the 1,348 primary-tier materials that drive an estimate - scored per trade by an LLM judge on material coverage and quantity Precision@25% (P@.25) and combined into a weighted composite. Under identical scoring from the raw PDF, seven frontier and open-weight models span composites of 35-61, and independent professional estimators - scored against the same reconciled gold standard - post 77.6% (65.5% coverage, 87.9% P@.25). Handoff-H1, working end-to-end from the raw PDF, reaches 81.6% (86.1% coverage, 78.8% P@.25): roughly 20 points above the strongest frontier agent, and above the independent estimators by pairing near-human quantity precision with coverage they do not reach. The evaluation harness is public for the open harbor framework; the blueprint sets and ground truth are available upon request for research use. Comments: 15 pages, 7 figures. Evaluation harness available on this https URL . Request data via e-mail to research@handoff.ai Subjects: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV) Cite as: arXiv:2608.15032 [cs.CL] (or arXiv:2608.15032v1 [cs.CL] for this version) https://doi.org/10.48550/arXiv.2608.15032 Focus to learn more arXiv-issued DOI via DataCite Submission history From: Bruno Chicelli [ view email ] [v1] Sat, 15 Aug 2026 04:34:51 UTC (1,365 KB) Full-text links: Access Paper: View a PDF of the paper titled Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints, by Bruno Chicelli and 5 other authors View PDF HTML (experimental) TeX Source view license Current browse context: cs.CL < prev | next > new | recent | 2026-08 Change to browse by: cs cs.AI cs.CV References & Citations NASA ADS Google Scholar Semantic Scholar export BibTeX citation Loading... BibTeX formatted citation × loading... Data provided by: Bookmark Bibliographic Tools Bibliographic and Citation Tools Bibliographic Explorer Toggle Bibliographic Explorer ( What is the Explorer? ) Connected Papers Toggle Connected Papers ( What is Connected Papers? ) Litmaps Toggle Litmaps ( What is Litmaps? ) scite.ai Toggle scite Smart Citations ( What are Smart Citations? ) Code, Data, Media Code, Data and Media Associated with this Article alphaXiv Toggle alphaXiv ( What is alphaXiv? ) Links to Code Toggle CatalyzeX Code Finder for Papers ( What is CatalyzeX? ) DagsHub Toggle DagsHub ( What is DagsHub? ) GotitPub Toggle Gotit.pub ( What is GotitPub? ) Huggingface Toggle Hugging Face ( What is Huggingface? ) ScienceCast Toggle ScienceCast ( What is ScienceCast? ) Demos Demos Replicate Toggle Replicate ( What is Replicate? ) Spaces Toggle Hugging Face Spaces ( What is Spaces? ) Spaces Toggle TXYZ.AI ( What is TXYZ.AI? ) Related Papers Recommenders and Search Tools Link to Influence Flower Influence Flower ( What are Influence Flowers? ) Core recommender toggle CORE Recommender ( What is CORE? ) Author Venue Institution Topic About arXivLabs arXivLabs: experimental projects with community collaborators arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website. Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them. Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs . Which authors of this paper are endorsers? | Disable MathJax ( What is MathJax? ) We gratefully acknowledge support from our major funders , member institutions , , and all contributors. About · Help · Contact · Subscribe · Copyright · Privacy · Accessibility · Operational Status (opens in new tab) Major funding support from

Related documents

• Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints#610986
• Machines, AI and the past//future of things#1035363
• Beyond Quantum Advantage: Improved Classical Algorithms for the Binary Paint Shop Problem#635788
• Beyond Quantum Advantage: Improved Classical Algorithms for the Binary Paint Shop Problem#633439
• AI Art is Theft: Labour, Extraction, and Exploitation, Or, On the Dangers of Stochastic Pollocks#86718