English(EN) Delegating Authorization to Misaligned Agents: Coalitional Alignment and Safe Control

新的AI控制框架允许将授权委托给未对齐的代理

作者 PulseAugur 编辑部 · [1 个来源] · 2026-09-15 04:00

研究人员开发了一个新的AI代理控制框架，特别适用于那些需要长时间运行的代理。该方法被称为“k-鲁棒联盟对齐”，允许将授权委托给其他AI代理，即使这些代理与人类目标不完全对齐。该方法通过确保主代理的表现达到或超过基线来保证安全，前提是审查小组满足某些条件。实验表明，即使容忍一些否决，集体审查也能在不要求个体代理对齐的情况下保持安全。 AI

影响引入了一种新颖的AI安全和控制方法，可能支持更复杂和自主的AI系统。

排序理由详细介绍AI控制新理论框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

Markov decision process

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 11 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 详细介绍AI控制新理论框架的学术论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, safety; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: Same-day; Cluster formed today. Ranking reflects the current source set at time of score.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Natalie Collina, Surbhi Goel, Aaron Roth, Sikata Bela Sengupta · 2026-09-15 04:00

将授权委托给未对齐的代理：联盟对齐与安全控制

arXiv:2609.15803v1 Announce Type: cross 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 conse…

本文如何被排名

报道来源 [1]

将授权委托给未对齐的代理：联盟对齐与安全控制

相关实体

相关话题