zkAgent: Verifiable LLM Agent Execution via One-Shot Transcript Proofs

본문 미리보기

LLM-based agents, which interleave large language model inference with external tool calls, are increasingly deployed in high-stakes settings. In real-world deployments, each model inference and provider-hosted tool execute behind the provider's API. Even when the agent loop runs on the user's device, these provider-executed steps still remain opaque to the user. This opacity creates an end-to-end integrity gap: a malicious provider may substitute the advertised model or fabricate tool observati