SOURCE-LINKED INTELLIGENCE
Delegating Authorization to Misaligned Agents: Coalitional Alignment and Safe Control
Long-running AI agents create a control problem: each action they take changes the state, which in turn affects the trajectory of future actions. If the agent is not fully aligned, then guaranteeing safety requires approving consequential actions before allowing them to be executed. But requiring human approval at every step makes attention a bottleneck. Delegating review to other AI agents raises the same alignment problem: the reviewers may themselves be misaligned. We identify a condition on a reviewing panel that is weaker than individual alignment yet necessary and sufficient for a guaran
Read original source ↗ Open in workspace
- recordType
- paper
- region
- Global
Evidence & attribution
- arXiv · AI, language, vision and robotics · 2026-09-14T16:12:41.000Z
First collected: 2026-09-20T09:41:04.278Z. This is not the publication date.