Track papers across labs, topics, and trends.
Search papers, labs, and topics across Lattice.
This paper introduces the Agent Flight Recorder, a system designed to create tamper-evident audit trails for long-horizon tool-using agents by capturing structured events that detail agent actions from intent to execution. By leveraging hash chaining and Merkle batching for tamper evidence, along with periodic on-chain anchoring, the system allows independent verification of actions without relying on a trusted intermediary. Evaluation results show that the system achieves 100% detection of tampering with minimal latency and storage overhead, significantly improving the reliability of agent action records in cross-organizational contexts.
Independent verification of agent actions is now possible without a trusted intermediary, thanks to a novel tamper-evident audit trail system.
Long-horizon agents execute thousands of actions, resulting in sequential failures rather than isolated errors. When a coding agent deletes a production database or a prompt injection spreads across agents, the incident raises questions of causality, authority, and non-repudiable third-party verification. The Agent Flight Recorder captures each agent action as a structured, canonically serialized event binding eight semantic fields from intent through execution to provenance. Hash chaining and Merkle batching provide tamper evidence and compact inclusion proofs. For cross-organizational disputes where no party's infrastructure qualifies as neutral ground, periodic on-chain anchoring of epoch roots lets any verifier with the disclosed payload and Merkle proof check the record independently, without pre-agreeing on a trusted intermediary. The on-chain footprint is minimal: each anchor stores a 32-byte epoch root and a back-pointer, and no event content touches the chain. We evaluate the system across five cumulative ablation configurations on synthetic agent workloads. The full system adds ~48 microseconds median per-event latency and 512 bytes per event. L2 anchoring costs $2.30 per 100K events at 100-event epochs. The full integrity stack detects edit, delete, reorder, and fork tampering at 100% with zero false positives. Structured forensic queries achieve 1.0 precision on guardrail and delegation lookups where unstructured text search yields 0.013 and 0.077 respectively.