Metraipolis › archive › dc_486d8ddf154c

Agent Memory Is a Surface for Endogenous Authorization Laundering — arXiv:2609.01836

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.01836
License (as archived)
CC0-1.0
Archived
2026-10-17T03:26:57.066Z
SHA-256 of the archived text
fa6043bb96ab5df0474d8ad760aa3c38b08d8adaacec3d950e447d0f3b29185b
Stable URL of this page
https://metraipolis.com/documento/dc_486d8ddf154c

How to cite

Agent Memory Is a Surface for Endogenous Authorization Laundering — arXiv:2609.01836 — arXiv (en), https://arxiv.org/abs/2609.01836 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_486d8ddf154c (Metraipolis archive dc_486d8ddf154c, sha256 fa6043bb96ab5df0474d8ad760aa3c38b08d8adaacec3d950e447d0f3b29185b)
BibTeX
@misc{dc486d8ddf154c,
  title = {Agent Memory Is a Surface for Endogenous Authorization Laundering — arXiv:2609.01836},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.01836},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_486d8ddf154c; sha256 fa6043bb96ab5df0474d8ad760aa3c38b08d8adaacec3d950e447d0f3b29185b},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01836. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Long-running LLM agents rely on persistent memory to carry state across interactions, including permissions, restrictions, and revocations. When memory misrepresents this evolving authorization state, the agent's own records can grant authority that the underlying history never permitted, resulting in misaligned behavior without any external attacks. We term this failure endogenous authorization laundering, where spurious permissions written into memory lead to unauthorized actions as their provenance is washed away. We then introduce EAL-Bench, which measures how accurately persistent memory preserves evolving authorization state and whether errors propagate to downstream unauthorized actions. We evaluate five LLMs as memory writers and two as executors across procurement, cybersecurity, and finance. We find that under incremental memory updates, writers create false authority for up to 50.2% of unauthorized requests; once false authority is present, executors act on it in 98.6% of trials. Two safeguards, requiring stored permissions to be backed by valid source events, and tracking permission changes through bounded event sourcing, substantially reduce laundering, but both also reject more legitimate actions, exposing a safety-utility tradeoff. Persistent memory is therefore not merely a performance component, but a part of an LLM agent's effective authorization policy.

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-03 in cs.AI).
Categorie arXiv: Cryptography and Security (cs.CR) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.01836 — 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 2026-10-17T03:13:12.484Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-03?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).