arXiv Artificial Intelligence

Agent Memory Is a Surface for Endogenous Authorization Laundering

Agent Memory Is a Surface for Endogenous Authorization Laundering

Quick summary

arXiv:2609.01836v1 Announce Type: cross Abstract: 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

Key takeaways

  • arXiv:2609.01836v1 Announce Type: cross Abstract: 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.

Why it matters

The importance of “Agent Memory Is a Surface for Endogenous Authorization Laundering” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.

Kaynak sitede devamını oku: arXiv Artificial Intelligence ↗