3 papers
cs.AI2026
Explanation-Bound Tool Execution for AI Agents: Server-Verified Action Claims Without Trusting Model Rationales
Genliang Zhu, Chu Wang
Tool-using agents expose structured calls but commonly attach free-form rationales. Such rationales are neither authorization nor reliable introspection. We present Explanation-Bou…
cs.AI2026
Intent-Governed Tool Authorization for AI Agents
Genliang Zhu, Chu Wang
Tool-using AI agents commonly operate under integration credentials whose static permissions exceed a user's current request. We present Intent-Governed Access Control (IGAC), a se…
cs.CR2026
OpenPort Protocol: A Security Governance Specification for AI Agent Tool Access
Genliang Zhu, Chu Wang, Ziyuan Wang +2
AI agents increasingly require direct, structured access to application data and actions, but production deployments still struggle to express and verify the governance properties…