Metraipolis › archive › dc_0c818e22ea51
VIGIL: Verifier-Informed Gated Improvement Loop for Spreadsheet Question Answering — arXiv:2610.04287
- Source
- arXiv
- Original
- https://arxiv.org/abs/2610.04287
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-06T05:24:26.052Z
- SHA-256 of the archived text
6fe2f82b39f90a8b169862328c3df4e5fe1d828596d0aa8ed923d3f7d6d13222- Stable URL of this page
https://metraipolis.com/documento/dc_0c818e22ea51
How to cite
VIGIL: Verifier-Informed Gated Improvement Loop for Spreadsheet Question Answering — arXiv:2610.04287 — arXiv, https://arxiv.org/abs/2610.04287 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0c818e22ea51 (Metraipolis archive dc_0c818e22ea51, sha256 6fe2f82b39f90a8b169862328c3df4e5fe1d828596d0aa8ed923d3f7d6d13222)
BibTeX
@misc{dc0c818e22ea51,
title = {VIGIL: Verifier-Informed Gated Improvement Loop for Spreadsheet Question Answering — arXiv:2610.04287},
howpublished = {arXiv},
url = {https://arxiv.org/abs/2610.04287},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0c818e22ea51; sha256 6fe2f82b39f90a8b169862328c3df4e5fe1d828596d0aa8ed923d3f7d6d13222},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv, https://arxiv.org/abs/2610.04287. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Enterprise agents should improve from delayed feedback without allowing every correction to rewrite system behavior. We study continual harness learning for corpus-level spreadsheet question answering. Building on FiCo (Find-then-Compute), a static retrieval-and-execution backbone, we introduce VIGIL (Verifier-Informed Gated Improvement Loop). Within a question, VIGIL verifies and repairs diversely prompted Structured Query Language (SQL) candidates. Across episodes, delayed labels update only a contract calibrator and query/result-column selector. The base model, prompts, retriever, and recorded candidate pool remain fixed in the continual-learning protocol. With the gold workbook and expected type supplied, the ungated and dual-gated full-replay variants reach 82.4% and 82.0% forward accuracy over 79 documents, from a 75.8% static baseline. The dual gate has the larger retrospective gain (2.7 versus 2.3 points), and its 6.3-point forward gain has a 95% t-interval of 5.6-6.9. In a separate stricter split that excludes 16 documents and 380 questions from fitting and online promotion, the accuracy-only gate raises mean held-out accuracy across ten final harnesses from 80.3% to 86.7%. Calibrator-only adaptation gains 5.9 points, close to the combined 6.4-point gain. Yet three of 26 gate-approved updates reduce held-out accuracy relative to their incumbents, so replay-buffer non-regression does not imply held-out non-regression. MiMoTable and external-task case studies test within-task verification and reuse the same promote-or-retain discipline. Overall, the results support bounded, auditable harness adaptation while revealing where finite replay gates fail to generalize beyond their promotion buffers. 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/2610.04287 — 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 2026-10-06T05:24:05.449Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).