Problem
Research questions and friction points this paper is trying to address.
Agent-to-Agent (A2A)
cross-organization workflows
case-evidence verification
large language model agents
evidence path
A2A-CaseVerify: Merkle-Linked Case-Evidence Verification for Cross-Organization A2A Workflows
🤖 AI Summary
This study addresses the absence of mechanisms for verifying the integrity and consistency of workflow evidence paths in cross-organizational Agent-to-Agent (A2A) communication. To bridge this trust verification gap in A2A interoperability, we propose a Merkle-linked, offline, case-level evidence support verification method. Specifically, A2A runtime objects are mapped into directed evidence graphs to generate Merkle roots, thereby constructing a deterministic offline verifier. Experimental results demonstrate that the proposed approach successfully validates legitimate data packets generated by both standard implementations and SDKs while precisely rejecting thirteen controlled mutations with accurate diagnostic codes returned. Consequently, this method effectively ensures the auditability and reliability of cross-system collaboration within decentralized agent ecosystems.
📝 Abstract
Agent-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. We present A2A-CaseVerify, a deterministic offline verifier that maps preserved A2A runtime objects, business events, and typed support edges to a directed case evidence graph. It commits A2A envelopes, event projections, and support edges, then combines event and edge leaves into a deterministic case Merkle root. The verifier returns SUPPORTED with status OK only when protection and profile-specific reconstruction checks pass. We evaluate one canonical supported healthcare-profile bundle and 13 controlled mutations. We separately test a valid bundle generated with the official Python A2A software development kit (SDK). In these tests, the canonical and SDK-generated bundles are accepted. All 13 mutations are rejected, and each returned reason-code set contains its targeted diagnostic code. A2A-CaseVerify adds offline case-level evidence-support verification to A2A interoperability.
Innovation
Methods, ideas, or system contributions that make the work stand out.
Agent-to-Agent (A2A)
Merkle tree
Case evidence graph
Offline verification
Cross-organization workflows
🔎 Similar Papers
No similar papers found.
