Metraipolis › archive › dc_89d4e1b85e32
ADF-EA: A Unified Execution Assurance System for Agent Device Foundation — arXiv:2609.30691
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.30691
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-08T01:37:43.726Z
- SHA-256 of the archived text
870e6c593ba85f7064e55f1e73742bb5ec1c8b9e08b9172234ca9d93669f2dd1- Stable URL of this page
https://metraipolis.com/documento/dc_89d4e1b85e32
How to cite
ADF-EA: A Unified Execution Assurance System for Agent Device Foundation — arXiv:2609.30691 — arXiv (en), https://arxiv.org/abs/2609.30691 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_89d4e1b85e32 (Metraipolis archive dc_89d4e1b85e32, sha256 870e6c593ba85f7064e55f1e73742bb5ec1c8b9e08b9172234ca9d93669f2dd1)
BibTeX
@misc{dc89d4e1b85e32,
title = {ADF-EA: A Unified Execution Assurance System for Agent Device Foundation — arXiv:2609.30691},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.30691},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_89d4e1b85e32; sha256 870e6c593ba85f7064e55f1e73742bb5ec1c8b9e08b9172234ca9d93669f2dd1},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.30691. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Agents based on large language models (LLMs) can access heterogeneous devices through tools and APIs, but reliable execution must account for unmet effects, uncertain outcomes, and changing prerequisites. A command may be acknowledged without producing its intended effect, while missing feedback may obscure an action that has already succeeded. We present Agent Device Foundation--Execution Assurance (ADF-EA), an architecture that connects agent planning and device execution through shared capability contracts. Device Capability Contracts (DCCs) unify invocation conditions, intended effects, evidence requirements, and recovery rules across heterogeneous interfaces. Agents use these contracts to plan, while the runtime applies the same semantics to authorize actions, verify effects, and govern continuation and completion. Persistent execution state retains verified progress, unresolved outcomes, and remaining budgets across plan revisions, enabling observation-based recovery, authorized retries, and necessary state repair. We formalize the execution lifecycle and establish conditional soundness properties for completion and recovery authorization. Evaluations span multiple LLMs, five agent frameworks, and simulated process-control, household, and robotic manipulation domains. Compared with direct invocation and existing execution-checking approaches, ADF-EA reduces false completion and unnecessary repetition, supports necessary state repair, prevents calls to unavailable capabilities, and preserves permitted task completion and recovery. These results demonstrate DCCs as a reusable semantic foundation for agent autonomy across heterogeneous devices, unifying capability-based planning, evidence-grounded execution, and authorized recovery within one architecture. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-28 in cs.MA). Categorie arXiv: Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.30691 — 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 2026-10-08T01:11:54.438Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-28?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).