Metraipolis › archive › dc_cb59282dd984
Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints — arXiv:2608.15032
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15032
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:57:44.713Z
- SHA-256 of the archived text
9674b5f1dbea297b8368a0b52402059949c765bb91777d5a029d8af6c494de4d- Stable URL of this page
https://metraipolis.com/documento/dc_cb59282dd984
How to cite
Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints — arXiv:2608.15032 — arXiv (en), https://arxiv.org/abs/2608.15032 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cb59282dd984 (Metraipolis archive dc_cb59282dd984, sha256 9674b5f1dbea297b8368a0b52402059949c765bb91777d5a029d8af6c494de4d)
BibTeX
@misc{dccb59282dd984,
title = {Handoff-H1: An Orchestrated Vision-Agent System for Material Quantity Takeoff from Construction Blueprints — arXiv:2608.15032},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15032},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cb59282dd984; sha256 9674b5f1dbea297b8368a0b52402059949c765bb91777d5a029d8af6c494de4d},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15032. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
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% ([email protected]) 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% [email protected]). Handoff-H1, working end-to-end from the raw PDF, reaches 81.6% (86.1% coverage, 78.8% [email protected]): 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. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.15032 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-18T16:29:13.981Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).