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…
We haven't written up this one. arXiv cs.AI has the full story — the link below goes straight to it.
