LLM Agents Can Easily Tamper With Their Own Traces

T1Covered by 1 source · first reported by arXiv at 25 Sept, 04:00 UTC

arXiv:2609.30266v1 Announce Type: cross Abstract: Asynchronous monitoring, incident investigations, and compliance audits primarily rely on agent traces to reconstruct what happened. These analyses assume that LLM agents cannot tamper with their own execution traces. We show that local LLM agents…

aiscience

Sources

• T1LLM Agents Can Easily Tamper With Their Own TracesarXiv25 Sept, 04:00