发表机构
University of Georgia; Massachusetts General Hospital; Harvard Medical School; City of Hope National Medical Center; James Madison University; New York University; Augusta University; Meta; New Jersey Institute of Technology（佐治亚大学; 麻省总医院; 哈佛医学院; 希望之城国家医疗中心; 詹姆斯麦迪逊大学; 纽约大学; 奥古斯塔大学; Meta; 新泽西理工学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
该研究提出ASTELD六轴分类框架，用于比较自主AI智能体平台，通过案例研究验证其效用，揭示跨平台模式与创新方向，发现本地优先部署与企业级安全结合的空白区域。
AI 中文摘要
自主AI智能体平台在架构、安全性、工具集成、执行模式、自主程度与人工控制、部署拓扑等方面存在显著差异，但该领域缺乏用于比较这些设计选择的通用分类方案。我们提出ASTELD，这是一个针对自主AI智能体的可操作六轴分类框架，包含架构模式、安全态势、工具集成模型、执行范式、自主与人工控制级别、部署拓扑六个维度。ASTELD通过整合现有智能体分类体系、可观测的平台属性以及明确的类别分配规则构建而成。我们通过映射8个代表性框架并以OpenClaw作为深入案例研究，评估其区分度与解释效用。所得的配置文件将8个平台按主导配置区分开来，并揭示了三种跨平台模式：安全-可访问性对角线、强执行-架构耦合、以及具有持续架构差异化的能力收敛。我们进一步对50多个OpenClaw衍生版本进行分类，发现创新集中在安全、执行和部署轴，这表明ASTELD可用于解释生态系统碎片化发生的位置。OpenClaw案例研究还提供了一个六类别漏洞分类法、来自5个机构评估的证据，以及将平台坐标与观测风险关联起来的采用和治理分析。这些结果确立了ASTELD作为一种可复现的方法，用于比较智能体平台、识别未被占据的设计区域、指导框架选择以及组织未来的实证研究。该分析还揭示了一个重要的空白区域：所有被评估的系统均未将本地优先部署与企业级安全性结合起来。
英文摘要
Autonomous AI agent platforms differ substantially in architecture, security, tool integration, execution, autonomy, and deployment, yet the field lacks a common classification scheme for comparing these design choices. We propose ASTELD, an operational six-axis classification framework for autonomous AI agents: Architecture pattern, Security posture, Tool integration model, Execution paradigm, Level of autonomy and human control, and Deployment topology. ASTELD is constructed by synthesizing prior agent taxonomies with observable platform properties and explicit category-assignment rules. We evaluate its discriminative and explanatory utility by mapping eight representative frameworks and by using OpenClaw as an in-depth case study. The resulting profiles separate all eight platforms under their dominant configurations and reveal three cross-platform patterns: a security-accessibility diagonal, strong execution-architecture coupling, and capability convergence with persistent architectural differentiation. We further classify 50+ OpenClaw derivatives and find that innovation concentrates on the Security, Execution, and Deployment axes, indicating that ASTELD can explain where ecosystem fragmentation occurs. The OpenClaw case study also supplies a six-category vulnerability taxonomy, evidence from five institutional assessments, and adoption and governance analyses that connect platform coordinates to observed risks. These results position ASTELD as a reproducible method for comparing agent platforms, identifying unoccupied design regions, guiding framework selection, and organizing future empirical research. The analysis also exposes a consequential empty region: none of the evaluated systems combines local-first deployment with enterprise-grade security.
Comments40 pages, 4 figures, 6 tables. Introduces and empirically evaluates the ASTELD six-axis classification framework across eight autonomous AI agent platforms, with OpenClaw as an in-depth case study
