Metraipolis › archive › dc_c4aa8ee76f7e
Maat: Independent Deterministic Contract-Based Governance for Multi-Agent LLM Workflows — arXiv:2609.34017
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.34017
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T20:54:14.934Z
- SHA-256 of the archived text
711c83a11796e31fc6ef02ffda79d8b52fbba2c59d5bb72795672f807b928239- Stable URL of this page
https://metraipolis.com/documento/dc_c4aa8ee76f7e
How to cite
Maat: Independent Deterministic Contract-Based Governance for Multi-Agent LLM Workflows — arXiv:2609.34017 — arXiv (en), https://arxiv.org/abs/2609.34017 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_c4aa8ee76f7e (Metraipolis archive dc_c4aa8ee76f7e, sha256 711c83a11796e31fc6ef02ffda79d8b52fbba2c59d5bb72795672f807b928239)
BibTeX
@misc{dcc4aa8ee76f7e,
title = {Maat: Independent Deterministic Contract-Based Governance for Multi-Agent LLM Workflows — arXiv:2609.34017},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.34017},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_c4aa8ee76f7e; sha256 711c83a11796e31fc6ef02ffda79d8b52fbba2c59d5bb72795672f807b928239},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.34017. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large-language-model multi-agent systems (LLM-MAS) introduce a characteristic reliability problem: an error produced by one agent can be accepted as context by downstream agents and propagate across the workflow. Many proposed safeguards rely on learned or LLM-based judges whose verdicts are themselves probabilistic; we ask whether a deterministic layer can instead stop contract-detectable handoff defects. We present Maat, a runtime governance layer that validates agent-to-agent handoffs against a versioned workflow contract, or anchor, with no language model in the validation or scoring path. We evaluate it in six controlled domain workflows (6-15 agents, 522 trials) with injected data-level defects and a deterministic seven-check rubric. Version 1 reported gains in all six workflows (2.9-26.5%). A post-publication audit found that three benchmark scorers credited any early halt as a prevented defect. On paired trials where the governed run completed or halted on a finding attributable to a verified defect, the rubric score changes by +7.7% to +29.1% in five workflows and is flat in software development; model-call cost falls 17-53% where attributable halts occur early. A hand review of all 94 governed-arm halts found 35 false alarms (37%), caused by validator defects rather than model behaviour; counting those halts as failed work, the governed arm scores below the ungoverned arm in four of six workflows. The results support deterministic handoff validation for contract-expressible defects and show that validator configuration and halt attribution must themselves be tested; they do not establish universal correctness, hallucination detection, or model-independent effectiveness. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-29 in cs.MA). Categorie arXiv: Software Engineering (cs.SE) ; Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA). Pagina del lavoro: https://arxiv.org/abs/2609.34017 — 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 2026-10-07T20:24:41.716Z dalla pagina https://arxiv.org/catchup/cs.MA/2026-09-29?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).