mlsanityData to 7 Oct 2026

Agent Flight Recorder: Tamper-Evident Audit Trails with On-Chain Anchoring for Long-Horizon Tool-Using Agents

arXiv 2609.01931 ↗First posted 1 Sep 2026cs.CR cs.MAcited by 2

On the map: LLM safety and security → Prompt injection and agent security

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Prompt injection and agent security, one of 12 directions in LLM safety and security. First posted on arXiv 1 Sep 2026.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

Similar, not cited

Close in wording, no citation either way

  1. 2026LEDGER: Claim-to-Evidence Trace Graphs for Auditing LLM Agents
  2. 2026From Agent Traces to Trust: A Survey of Evidence Tracing and Execution Provenance in LLM Agents
  3. 2026MAP-Graph: Provenance-Aware Shared Memory for Multi-Agent Workflows
  4. 2026SpecGuard: Proving a Task Is Broken Before the Agent Cheats
  5. 2026Turning Interaction History into Execution State: A Runtime Layer for Long-Horizon Coding Agents
  6. 2026Observability for Delegated Execution in Agentic AI Systems
  7. 2026Canonical Procedural Actions: An Auditable Annotation Protocol for Tool-Use Agent Traces
  8. 2026AgentXploit: Autonomous Repository-to-Runtime Red-Teaming for AI Agents