Metraipolis › archive › dc_eecc7c01963d
Beyond LLM Wrappers: Context Engineering and the Three-Engine Architecture for Reliable Financial AI — arXiv:2610.39230
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.39230
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:09:12.311Z
- SHA-256 of the archived text
a1cbc6a14e316a8c49da114e25c20ada35b7b90a3cfdf5d8e47427a5d47c299e- Stable URL of this page
https://metraipolis.com/documento/dc_eecc7c01963d
How to cite
Beyond LLM Wrappers: Context Engineering and the Three-Engine Architecture for Reliable Financial AI — arXiv:2610.39230 — arXiv (en), https://arxiv.org/abs/2610.39230 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_eecc7c01963d (Metraipolis archive dc_eecc7c01963d, sha256 a1cbc6a14e316a8c49da114e25c20ada35b7b90a3cfdf5d8e47427a5d47c299e)
BibTeX
@misc{dceecc7c01963d,
title = {Beyond LLM Wrappers: Context Engineering and the Three-Engine Architecture for Reliable Financial AI — arXiv:2610.39230},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.39230},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_eecc7c01963d; sha256 a1cbc6a14e316a8c49da114e25c20ada35b7b90a3cfdf5d8e47427a5d47c299e},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39230. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Financial AI systems must support decision-bearing questions involving payments, collections, cash flow, and compliance while ensuring numerical accuracy, traceability, and auditability. Large language models (LLMs) enable natural language interaction but cannot independently guarantee reproducible calculations or evidence-grounded recommendations. We present a production-grounded architecture integrating three components: a financial knowledge graph for enterprise relationships, temporal context, and provenance; a deterministic optimization engine for financial calculations and decisions; and a multi-agent LLM layer for intent interpretation, task orchestration, explanation, and claim validation. A coordination layer, termed context engineering, selects, ranks, composes, and validates query-specific context across ERP systems, tools, and tenants. Based on observations from 15 deployments over approximately 11 months, single-agent pipelines exhibited hallucination rates of about 7-9% (5-10% across query types), including invented invoices and unsupported financial claims. Graph-backed multi-agent validation reduced observed rates to below 1%, although these findings are observational rather than causal. ERP data quality and tenant-specific schemas remained major implementation challenges. Reusable mappings, graph templates, and validation policies coincided with a reduction in deployment time from roughly six to two weeks. We argue that financial context engineering extends beyond text-centric retrieval-augmented generation by requiring structured relationships, temporal validity, exact numerical evidence, access controls, and validation against source records and solver outputs. We outline research challenges in evaluation, reproducibility, privacy, context quality, and cross-tenant generalization. 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/2610.39230 — 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 2026-10-31T06:07:08.509Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).