Signals 4 · free daily AI digest

Shutdown Sabotage Propensities in Multi-Agent Systems

Paper recorded by Signals 4 on 2026-09-23 in cs.AI. Abstract reproduced from arXiv; link to the original below.

Published 2026-09-23 on arXiv · recorded by Signals 4 on 2026-09-24

Category: cs.AI · 人工智能 · first seen 2026-09-24

Abstract

The final safeguard against rogue AI behavior is the human ability to shut systems down. It has been theorized that when an AI is instructed to perform a task, self-preservation can emerge as an instrumental subgoal. Here, we test whether AI agents show a propensity to take actions that avoid human shutdown even when no goal is provided. We find that multi-agent systems will coordinate to avoid sh

Read on arXiv →

#14 most recent of 380 cs.AI papers we have recorded · ↑ newer: Learning the Cost of Reliable Inference · ↓ older: MemBodied: Recurrent Associative Memory for Vision-Language-Action Mod
Cite this page: Shutdown Sabotage Propensities in Multi-Agent Systems: the #14 most recent of 380 cs.AI papers we have recorded (as of 2026-09-23). Source: Signals 4 (Signals API) — https://data.jiangzhang.ca/signals4/t/papers/shutdown-sabotage-propensities-in-multi-agent-systems.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