Skip to content
InfoResearchPreprintLLM-specific

Securing and Auditing Long-Horizon LLM Agents: State-Transfer Auditing and Controls in the Agent Harness

Published
Record updated
View JSON

Summary

This research presents a state-transfer audit architecture for the agent harness of long-horizon LLM agents. Each transfer boundary gets an audit point that emits a hash-chained record, separating deterministic checks from model-based semantic checks. A reference middleware evaluated across 240 multi-step fault-injection trajectories showed that these records localize root causes and catch cross-transfer violations missed by lifecycle and tool-only logs, at microsecond deterministic overhead.