Metraipolis › archive › dc_a29a05d7f044

CRAFT: An Agentic Spreadsheet Form Filling System with Template Awareness — arXiv:2610.04437

Source
arXiv
Original
https://arxiv.org/abs/2610.04437
License (as archived)
CC0-1.0
Archived
2026-10-06T05:24:33.017Z
SHA-256 of the archived text
daaac488c573f2fe1a8869155c0907e902ae2e267053527d26bca142d96c79f5
Stable URL of this page
https://metraipolis.com/documento/dc_a29a05d7f044

How to cite

CRAFT: An Agentic Spreadsheet Form Filling System with Template Awareness — arXiv:2610.04437 — arXiv, https://arxiv.org/abs/2610.04437 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a29a05d7f044 (Metraipolis archive dc_a29a05d7f044, sha256 daaac488c573f2fe1a8869155c0907e902ae2e267053527d26bca142d96c79f5)
BibTeX
@misc{dca29a05d7f044,
  title = {CRAFT: An Agentic Spreadsheet Form Filling System with Template Awareness — arXiv:2610.04437},
  howpublished = {arXiv},
  url = {https://arxiv.org/abs/2610.04437},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a29a05d7f044; sha256 daaac488c573f2fe1a8869155c0907e902ae2e267053527d26bca142d96c79f5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04437. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Spreadsheet form filling requires agents to consolidate external evidence, ground values to precise cells, and preserve irregular template structure. Errors in early edits can overwrite labels or misalign fields, undermining later decisions. We propose CRAFT, a template-aware agent framework that connects reflective validation to constrained local repair. Instead of treating reflection as a free-form request to regenerate the workbook, CRAFT grounds detected errors to spreadsheet regions, restores corrupted template state when necessary, and re-grounds plausible writable slots before subsequent edits. A Rectangle-Aware Slot Grounder (RASG) proposes writable cells, while label-slot hints and protected regions constrain subsequent edits. We introduce FormFillBench, with 327 forms across Instruction-Only and Multi-File tracks. Compared with the strongest baselines, CRAFT improves pair accuracy by 8.51 and 23.38 percentage points on these tracks, respectively. Component-removal experiments support structural adjudication and slot re-grounding within the pipeline, and the framework retains its relative advantage among the methods evaluated with a second backbone. The code and benchmark FormFillBench are available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.04437 — 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 2026-10-06T05:24:05.470Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).