arXiv AI By Genliang Zhu, Chu Wang

Authorization Revocation for Long-Running AI Agents: Root-Scoped Quiescence under Delegation and Asynchronous Execution

Read the original on arXiv AI →

The Flow has not summarised this story yet — read it at arXiv AI.

arXiv AI
Oct 2

Authorization for Self-Modifying AI Agent Populations: Conserving Authority across Replacement, Forking, and Rollback

The paper introduces "authorization succession," a framework that preserves authority across self‑modifying AI agent populations that can replace, fork, or roll back. It defines a protocol binding each generation to a manifest, root, unique parent, lineage, and population sequence, and establishes invariants that control root‑lifetime consumption and population exposure. The authors prove properties such as population‑safe succession, fork conservation, and rollback non‑reminting, and validate the approach with an executable evaluation covering 32 decisions and external adapters for two mutation systems.

By Genliang Zhu, Chu Wang
arXiv AI
Sep 15

AcquireBound: Runtime Authorization for Resources Acquired by AI Agents

AcquireBound is a runtime authorization framework that ensures AI agents can safely acquire and activate resources such as compute, credentials, and services. It quarantines acquired outputs, resolves their capabilities through authenticated evidence, and activates them only after verifying a manifest, provenance, and relational constraints. The system demonstrates strong safety properties, passing extensive benign and unsafe trace tests across multiple resource classes.

By Genliang Zhu