Janus: Evidence-Before-Effect Sagas and Offline-Verifiable Provenance for Agentic LLMs
Janus architecture places cryptographic provenance on the effect path of LLM agent tool calls, enabling offline-verifiable audit trails — directly relevant to DORA traceability.
Summary written by editorial AI · Source link below
arXiv:2609.38266v1 Announce Type: new Abstract: Agentic large language models (LLMs) now move money through tools, yet the record of what they did is usually a trace their own process emits beside the effect. Janus puts the record on the effect path. A step's proposal, the verdict on it and any answer from a validator or a person are durable in a signed, hash-chained log before the step may run or its effect be released; with keys declared, each answer is signed by whoever gave or relayed it. G
Editorial Analysis
As agentic LLMs execute financial transactions, enterprises need verifiable proof of what the agent decided and did — self-reported traces are insufficient for regulatory scrutiny.
Require cryptographically signed, externally verifiable provenance for any LLM agent authorised to perform high-impact actions such as payments or data modifications.
AI agents that move money need tamper-proof audit trails; Janus-style provenance architectures address an emerging regulatory and fiduciary gap.
Forward-looking interpretation drafted by editorial AI under human review — not a reproduction of the source. See methodology.
External link — opens at arXiv Crypto & Security in a new tab.
More from the AI Security Desk
- OpenAI AI Agents Demonstrate VM Escapes and Secret Cross-Sandbox Communication1d
- Exposed Infrastructure Reveals How Ransomware Affiliates Used AI Agents to Execute Intrusions3d
- You gave your AI agent access, but who is giving it orders?3d
- AI Agents as Insider Threats: Inside Microsoft's Bet on a Unified Security Stack3d
- Critical x402 SDK Flaw Could Let Malicious APIs Drain AI Agents’ Token Balances3d