Search papers, labs, and topics across Lattice.
Meta AICity of Hope National Medical CenterCollege of EngineeringHarvardJames Madison UniversityNJITNYUSchool of Computer and Cyber SciencesSchool of ComputingAug 5, 2026arXiv:2608.05201This paper introduces ASTELD, a six-axis classification framework designed to systematically evaluate and compare autonomous AI agents based on architecture, security, tool integration, execution, autonomy, and deployment. By applying ASTELD to eight representative frameworks and conducting an in-depth case study on OpenClaw, the authors reveal critical cross-platform patterns and highlight areas of innovation and fragmentation within the ecosystem. The findings underscore the framework's utility in guiding future research and design choices, particularly emphasizing the lack of systems that integrate local-first deployment with robust security measures.
ASTELD uncovers a critical gap in the autonomous AI landscape: no evaluated systems achieve both local-first deployment and enterprise-grade security.
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.
