Runtime Authorization of Self-Generated Subgoals in Long-Horizon Tool-Using AI Agents

Excerpt

arXiv:2610.04975v1 Announce Type: new Abstract: Long-horizon tool-using AI agents create subgoals, replan, delegate work, and compose sibling results. Per-tool permission checks cannot establish that a changing goal graph remains within the principal-approved task. We address this authorization gap in a finite structured domain with one principal and one authorization root. Each proposed goal-graph mutation carries a version-bound witness that its continuation traces, resources, obligations, inv