A2A-CaseVerify: Merkle-Linked Case-Evidence Verification for Cross-Organization A2A Workflows
A2A-CaseVerify uses Merkle roots to check that agent workflow claims have complete evidence paths.
A2A-CaseVerify maps preserved agent-to-agent runtime objects, business events, and typed support edges into a directed case evidence graph and a deterministic case Merkle root. It returns SUPPORTED only when protection and profile-specific reconstruction checks pass. A canonical healthcare-profile bundle and a bundle from the official Python A2A SDK were accepted, while all 13 controlled mutations were rejected with their targeted diagnostic codes.
- Offline verifier commits A2A envelopes, events, and support edges
- Combines event and edge leaves into a case Merkle root
- Canonical and official Python A2A SDK bundles were accepted
- All 13 controlled mutations were rejected with targeted codes
From the original article
1 min read at arxiv.orgAgent-to-Agent (A2A) communication enables large language model (LLM) agents to exchange tasks, messages, and artifacts across organizations. A valid message alone does not establish that a final workflow claim is supported by a complete, ordered, and case-consistent evidence path.
By Adil Alshammari · arxiv.org
A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.