arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2502.01635cs.SEcs.AI
收藏

AI智能体指数

The AI Agent Index

Massachusetts Institute of Technology(麻省理工学院);Stanford University(斯坦福大学);University of Warwick(华威大学);Harvard University(哈佛大学);Hebrew University(希伯来大学)
Stephen Casper, Luke Bailey, Rosco Hunter, Carson Ezell, Emma Cabalé, Michael Gerovitch, Stewart Slocum, Kevin Wei, Nikola Jurkovic, Ariba Khan, Phillip J. K. C… 展开作者

Stephen Casper, Luke Bailey, Rosco Hunter, Carson Ezell, Emma Cabalé, Michael Gerovitch, Stewart Slocum, Kevin Wei, Nikola Jurkovic, Ariba Khan, Phillip J. K. Christoffersen, A. Pinar Ozisik, Rakshit Trivedi, Dylan Hadfield-Menell, Noam Kolt

AI总结:

本文推出首个记录已部署智能体AI系统信息的公共数据库AI Agent Index,系统记录其技术组件、应用领域和风险管理实践,发现开发者提供的安全信息有限。

摘要:

领先的AI开发者和初创企业正日益部署能够在有限人类参与下规划和执行复杂任务的智能体AI系统。然而,目前尚无结构化框架来记录智能体系统的技术组件、预期用途和安全特性。为填补这一空白,我们推出了AI Agent Index,这是首个记录当前已部署智能体AI系统信息的公共数据库。对于符合纳入标准的每个系统,我们基于公开信息和与开发者的通信,记录了系统的组件(如基础模型、推理实现、工具使用)、应用领域(如计算机使用、软件工程)以及风险管理实践(如评估结果、护栏)。我们发现,尽管开发者通常提供关于智能体系统能力和应用的充足信息,但他们目前提供的安全和风险管理实践信息有限。AI Agent Index可在https://aiagentindex.mit.edu/在线获取。

英文摘要:

Leading AI developers and startups are increasingly deploying agentic AI systems that can plan and execute complex tasks with limited human involvement. However, there is currently no structured framework for documenting the technical components, intended uses, and safety features of agentic systems. To fill this gap, we introduce the AI Agent Index, the first public database to document information about currently deployed agentic AI systems. For each system that meets the criteria for inclusion in the index, we document the system's components (e.g., base model, reasoning implementation, tool use), application domains (e.g., computer use, software engineering), and risk management practices (e.g., evaluation results, guardrails), based on publicly available information and correspondence with developers. We find that while developers generally provide ample information regarding the capabilities and applications of agentic systems, they currently provide limited information regarding safety and risk management practices. The AI Agent Index is available online at https://aiagentindex.mit.edu/

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。

↑