Metraipolis › archive › dc_cf75da2bd813
Auditable Belief Updates as a Missing Safety Layer for LLM-Powered Multi-Agent Systems — arXiv:2610.38869
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.38869
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-31T06:09:05.605Z
- SHA-256 of the archived text
c69a17e502ea4d95ff05f3c73491d10f11c5a553f198ddf7c749df40cb304821- Stable URL of this page
https://metraipolis.com/documento/dc_cf75da2bd813
How to cite
Auditable Belief Updates as a Missing Safety Layer for LLM-Powered Multi-Agent Systems — arXiv:2610.38869 — arXiv (en), https://arxiv.org/abs/2610.38869 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf75da2bd813 (Metraipolis archive dc_cf75da2bd813, sha256 c69a17e502ea4d95ff05f3c73491d10f11c5a553f198ddf7c749df40cb304821)
BibTeX
@misc{dccf75da2bd813,
title = {Auditable Belief Updates as a Missing Safety Layer for LLM-Powered Multi-Agent Systems — arXiv:2610.38869},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.38869},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf75da2bd813; sha256 c69a17e502ea4d95ff05f3c73491d10f11c5a553f198ddf7c749df40cb304821},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.38869. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Large Language Models (LLMs) are increasingly being used as cognitive interfaces that shape how users interpret evidence, communicate, and make decisions. As deployed systems become more multimodal, tool-using, and multi-agent, safety failures no longer arise only from isolated harmful outputs, but also from how agents update, store, and propagate epistemic commitments across retrieval, memory, tools, and peer communication. In this paper, we define belief as an engineering abstraction for evidence-based commitments that guide downstream action. Building on this view, we propose the Explicit Belief Multi-Agent System (EB-MAS), which externalizes belief states into a structured substrate, uses belief operators to propose candidate updates, and applies a Cognitive Firewall to bound or reject updates that are weakly evidenced but strongly driven by vulnerability cues. We also discuss the risk of group belief at the group level, including manufactured consensus, collusion, and cascading misinformation, and outline practical integration challenges around grounding, false positives, scalability, and ethical misuse. Therefore, scalable agent safety requires not only better output filtering or stronger base models, but also explicit interfaces for tracing, calibrating, and constraining belief revision at runtime. 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/2610.38869 — 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 2026-10-31T06:07:08.495Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).