Metraipolis › archive › dc_47965ec53eef
Formal Verification of Agentic Systems over Operational Data — arXiv:2608.03609
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.03609
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T12:16:29.939Z
- SHA-256 of the archived text
1c506874d6d88e5436808ce2fbf91197874db2da445fb9266c3105813b2e28d4- Stable URL of this page
https://metraipolis.com/documento/dc_47965ec53eef
How to cite
Formal Verification of Agentic Systems over Operational Data — arXiv:2608.03609 — arXiv (en), https://arxiv.org/abs/2608.03609 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_47965ec53eef (Metraipolis archive dc_47965ec53eef, sha256 1c506874d6d88e5436808ce2fbf91197874db2da445fb9266c3105813b2e28d4)
BibTeX
@misc{dc47965ec53eef,
title = {Formal Verification of Agentic Systems over Operational Data — arXiv:2608.03609},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.03609},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_47965ec53eef; sha256 1c506874d6d88e5436808ce2fbf91197874db2da445fb9266c3105813b2e28d4},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.03609. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agentic systems driven by large language models (LLMs) are increasingly deployed in real-world workflows where they act on persistent operational data. Before deployment, these systems need to be verified against business requirements that govern workflow execution and data evolution. However, existing approaches do not provide such system-level guarantees, as they mainly constrain or analyse behaviour at the agent's interface level. We study here the verification of agentic systems comprising a single LLM and a tool orchestration harness over relational operational data. We formalise them as Stateful Tool-Enabled Agentic Deployments (STEADs), give their semantics, define the problem of verifying them against First-Order Computation Tree Logic (FO-CTL) specifications, and show that it is undecidable. We identify sufficient conditions for exact preservation of FO-CTL specifications under a finite-domain restriction, over which verification is PSPACE-complete. The key requirement is that renaming opaque identifiers in the data must correspondingly rename the selected tool calls. We show that LLM-driven agents can violate this condition and introduce a canonical deployment wrapper that guarantees it for arbitrary base agents while preserving already-equivariant behaviour. We prove that computing canonical representations required by this construction is graph-isomorphism-hard. Finally, we illustrate our framework on an LLM agent orchestrating a case-management workflow. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-05 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2608.03609 — 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 2026-10-31T12:05:52.822Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-05?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).