Matoi: Selective Revalidation of Consequence Evidence for Agent Authorization

cs.CR, cs.AI

Submitted: 2026-10-15

Updated: 2026-10-15

Comments: 55 pages, 4 figures. Includes an 18-page technical manuscript and a 33-page detailed supplement as ancillary files. Research preprint; not peer reviewed

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Agent Approval Laundering: Transitive Effects Beyond the Approved Invocation
• When Valid Tool Calls Change Meaning: Formation-Consistent Dispatch for LLM Agents
• Proof-Carrying Agent Actions: Model-Agnostic Runtime Governance for Heterogeneous Agent Systems
• CAVA: Canonical Action Verification and Attestation for Runtime Governance of Agentic AI Systems
• ZeroGate: Trust-Preserving Fast Paths for Governed AI Agent Runtimes
• VEPA: Verified Evolving Formal Policy for Lifelong LLM Agent Guardrails
• APEX: Active Protection at Execution Boundaries for LLM Agents
• HarnessSecurity-Bench: Do Security Mechanisms Really Protect Coding Agent Harnesses?

Related papers

• SoK: AI-Augmented Binary Reversing
• Relaxed Sender Anonymity for CBDC Interbank Settlement: A Zero-Knowledge Approach on Permissioned EVM
• Calibration-Family Overfit: Why Trusted Sabotage Monitors Don't Transfer Across Lineages
• Estimating the Social Cost of Corporate Data Breaches
• Efficient Fuzzy PSI under One-Sided Assumptions
• Sealing the Audit-Runtime Gap for LLM Skills