Signals 4 · free daily AI digest

Delegating Authorization to Misaligned Agents: Coalitional Alignment and Safe Control

Paper recorded by Signals 4 on 2026-09-14 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-14 on arXiv · recorded by Signals 4 on 2026-09-15

Category: cs.AI · 人工智能 · first seen 2026-09-15

Abstract

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

Read on arXiv →

#79 most recent of 300 cs.AI papers we have recorded · ↑ newer: Atria Dawn: The Dawn of Agentic Superintelligence · ↓ older: When Should a World Model Move? Loss-Conditioned State Execution
Cite this page: Delegating Authorization to Misaligned Agents: Coalitional Alignment and Safe Control: the #79 most recent of 300 cs.AI papers we have recorded (as of 2026-09-14). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/delegating-authorization-to-misaligned-agents-coalitional-alignment-and-safe-con.html
Free to quote with attribution to “Signals 4 (Signals API)”. Machine-readable: papers.json
Related: More cs.AI papers · arXiv signals · All papers · Today in AI
Get 4 AI signals a day by email — free.
Subscribe free → See all plans →
Get 4 AI signals a day by email — free
All models · All repos · By company · Daily editions