FAVA: Formal Authorization for Verified Agents with Evidence-Backed Permission Graphs

본문 미리보기

arXiv:2607.27267v1 Announce Type: new Abstract: Large language model (LLM) agents autonomously interleave semantic reasoning with complex system operations. In these dynamic environments, static tool-level permissions are fundamentally insufficient; safe authorization is highly context-dependent and heavily reliant on evolving runtime states and data flows. We present FAVA (Formal Authorization for Verified Agents), a permission-carrying authorization framework for agent execution. FAVA utilize