Skip to content

ZeroGate: Trust-Preserving Fast Paths for Governed AI Agent Runtimes

Sep 2026 · arXiv.org · Vol abs/2609.25443 · 1 citation · 40 references
Computer Science

TL;DR

A conditional decision-preservation proposition: successful local admission implies that a specified synchronous policy would authorize the same action at the admission point, provided approval is sound, all policy dependencies are represented and current, observations are faithful, and consumption is atomic.

Abstract

Moving authorization earlier can shorten an agent's dispatch boundary without removing authorization work. It can also admit an action whose payload, authority, or relevant state has changed. ZeroGate separates exact-action approval from durable local admission: an issuer signs a short-lived ActionPass, and a trusted runtime adapter reconstructs the final action before a local gate checks its binding and consumes its nonce. A SQLite transaction couples nonce consumption, applicable quota updates, and an admission receipt. We state a conditional decision-preservation proposition: successful local admission implies that a specified synchronous policy would authorize the same action at the admission point, provided approval is sound, all policy dependencies are represented and current, observations are faithful, and consumption is atomic. The implementation alone establishes neither current-world freshness nor exactly-once remote effects. Evaluation separates authored semantic fixtures, controlled concurrency and crash experiments, and an Azure Blob study comparing synchronous and prepared execution through the same issuer and gate. Both modes mint an exact-action pass; lifecycle latency includes preparation and prepared-batch dwell. Across 4800 cloud attempts, prepared worker-admission-to-dispatch p95 ranges from 9.802 to 11.374 ms, versus 25.018 to 334.000 ms synchronously, across the tested concurrency levels. Prepared mean complete lifecycle is longer at every level: the boundary improvement is not a net speedup. The contribution is an explicit revalidation contract, a durable reference boundary, and an auditable comparison of where authorization cost is paid, not a new cryptographic primitive or a universal performance frontier.

View source

Similar papers

Sep 2026

CATP: Design and Evaluation of Local Agent Authorization and Audit Evidence

A signed authorization record authenticates what a signer asserted, but does not by itself establish that the assertion agrees with the policy and action used for a runtime decision. CATP specifies the bindings needed to carry a local pre-execution decision into offline-verifiable evidence. Its hook commits to the enfo...

Ling-Feng Zhou · 2 citations
Preprint Aug 2026

A Policy Algebra for Trust-Preserving Agentic AI Execution

A policy algebra is proposed that defines the reliability envelope within which agent capability may be exercised and provides researchers and practitioners with formal correctness conditions, executable decision semantics, and trace evidence for building agents that are not only capable, but reliably capable.

Bhaskar Tripathi, Anurag Kumar, R. Kumar et al. · 0 citations
Preprint Aug 2026

AID-Guard: Stateful Authorization for Delegated Agent Effects

This work presents AID-Guard, a stateful authorization-to-effect closure protocol that revalidates the approved request and provider state at commit, retains one reservation under ambiguity, and permits release or one successor only after a terminal result or certified no effect with a delivery fence.

Yingzhe Tong, Le-Yu Dai, Song-Hui Guo · 9 citations
Sep 2026

Runtime Authorization for Resources Acquired by AI Agents

A provenance-bounded runtime authorization architecture that quarantines acquired outputs, resolves their actual capabilities from authenticated provider evidence through a versioned resolver, and activates them only through a current activation transaction that checks the resolved manifest, provenance, epochs, and a d...

Gen-Liang Zhu, Chu Wang · 0 citations
Preprint Sep 2026

ResidualAuth: What Authorization State Must Language Agents Preserve under Revocable Delegation?

This work introduces ResidualAuth, a theory-grounded framework characterizing the authorization state agent systems must preserve and evaluating its maintenance and use, and proves that exponentially many distinct residual states can nevertheless agree on who can reach whom through delegation paths.

M. Choi, Seokho Jeong, Sian Choi et al. · 2 citations
#artificial intelligence Conference Open access Sep 2026

Autonomy in Check: Governor-Mediated Adaptive Security at the Edge

This paper proposes a split-control architecture in which an untrusted planner emits typed security intents, a deterministic governor checks each intent against safety, resource, temporal-stability, and proportionality invariants, and only admitted actions are bound to signed receipts and compiled into pre-installed eB...

Ijaz Ahmad, Ijaz Ahmad, Flavio Esposito et al. · 0 citations

Related blog posts

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.