AI Agents with Decentralized Identifiers and Verifiable Credentials
This work provides a conceptual and prototypical solution for cross-domain trust in agentic AI, but it is incremental as it applies existing identity standards to a new domain.
The paper addresses the lack of trust establishment mechanisms in LLM-based AI agents by proposing a framework that equips agents with self-sovereign digital identities using W3C Decentralized Identifiers and Verifiable Credentials. A prototype demonstrates technical feasibility but reveals limitations when the LLM controls security procedures.
A fundamental limitation of current LLM-based AI agents is their inability to build differentiated trust among each other at the onset of an agent-to-agent dialogue. However, autonomous and interoperable trust establishment becomes essential once agents start to operate beyond isolated environments and engage in dialogues across individual or organizational boundaries. A promising way to fill this gap in Agentic AI is to equip agents with long-lived digital identities and introduce tamper-proof and flexible identity-bound attestations of agents, provisioned by commonly trusted third parties and designed for cross-domain verifiability. This article presents a conceptual framework and a prototypical multi-agent system, where each agent is endowed with a self-sovereign digital identity. It combines a unique and ledger-anchored W3C Decentralized Identifier (DID) of an agent with a set of third-party issued W3C Verifiable Credentials (VCs). This enables agents at the start of a dialog to prove ownership of their self-controlled DIDs for authentication purposes and to establish various cross-domain trust relationships through the spontaneous exchange of their self-hosted DID-bound VCs. A comprehensive evaluation of the prototypical implementation demonstrates technical feasibility but also reveals limitations once an agent's LLM is in sole charge to control the respective security procedures.