arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 2502.18359cs.CY
收藏

负责任的人工智能智能体

Using Agency Law to Tame AI Agents

Georgia Institute of Technology(佐治亚理工学院);Yale Law School(耶鲁法学院);Google, Inc.(谷歌公司);Scheller College of Business(谢勒商学院);Emory Law School(埃默里法学院);Sandra Day O’Connor College of Law(桑德拉·戴·奥康纳法学院);Arizona State University(亚利桑那州立大学);Georgia Tech School of Interactive Computing(佐治亚理工学院互动计算学院)

Deven R. Desai, Mark O. Riedl

AI总结:

针对AI智能体可能引发的恶意行为等担忧,本文提出利用软件交互约束和价值对齐方法构建负责任AI智能体,并主张不赋予其法律人格,人类应负责其行为。

摘要:

得益于大型语言模型的进步,一种新型软件智能体——人工智能(AI)智能体——已进入市场。OpenAI、Google、Microsoft 和 Salesforce 等公司承诺,其 AI 智能体将从生成被动文本转向执行任务。AI 智能体不会仅仅提供旅行行程,而是会预订你旅行中的所有环节。AI 智能体不会仅为社交媒体帖子生成文本或图像,而是会在众多社交媒体平台上发布内容。AI 智能体的潜在力量加剧了法律学者的担忧,他们认为 AI 智能体将助长恶意商业行为、操纵人类、猖獗的诽谤以及知识产权损害。这些学者呼吁在 AI 智能体造成混乱之前对其进行监管。本文直面围绕 AI 智能体的这些担忧。文章表明,一个软件与另一个软件交互的核心方面创造了约束 AI 智能体的方式,使得恶意或不良行为不太可能发生,甚至可能比旨在约束人类智能体的规则更为有效。文章还提出了一种利用计算机科学的价值对齐方法来提高用户采取行动预防或纠正 AI 智能体操作的能力。这种方法还带来额外好处,即帮助 AI 智能体与用户-AI 智能体交互的规范保持一致。这些实践将促成期望的经济结果并减轻感知到的风险。文章还认为,无论 AI 智能体看起来多么像人类智能体,它们都不需要也不应被赋予法律人格地位。简而言之,人类对 AI 智能体的行为负责,本文为人类如何构建和维护负责任的 AI 智能体提供了指南。

英文摘要:

Artificial Intelligence (AI) Agents have entered the marketplace. By some estimates, AI Agents, which promise to execute tasks and even take over your computer to do so, present a more than $400 billion market. The potential power of AI Agents has fueled legal scholars' fears that AI Agents will enable rogue commerce, human manipulation, rampant defamation, and infringement of intellectual property rights. These scholars are calling for regulation before AI Agents cause havoc. This Article addresses concerns about AI Agents head-on. The Article leverages the socio-legal issues presented by agency law to identify potential problems. It then asks how computer science can solve those problems rather than trying to take rules for humans and impose them on software. This approach shows that core aspects of modern software engineering, particularly client server architectures, address several of those concerns in ways quite different from---and arguably stronger than---how the law would discipline a human agent.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑