Related papers: ASTELD: A Six-Axis Classification Framework for Autonomous AI Agents - Design, Evaluation, and an OpenClaw Case Study

ASTELD: A Six-Axis Classification Framework for Autonomous AI Agents - Design, Evaluation, and an OpenClaw Case Study

URL: http://arxiv.org/abs/2608.05201v1
Date: Wed, 05 Aug 2026 05:05:20 GMT
Title: ASTELD: A Six-Axis Classification Framework for Autonomous AI Agents - Design, Evaluation, and an OpenClaw Case Study
Abstract summary: ASTELD is an operational six-axis classification framework for autonomous AI agents.<n>It is constructed by synthesizing prior agent with observable platform properties and explicit category-native rules.
Score: 31.080136605890004
License: http://creativecommons.org/licenses/by/4.0/
Abstract: 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.

Related papers

Risk Architecture for AI-Native Engineering Teams: An Organizational Framework for Agentic System Governance [0.0]
This paper contributes a seven-dimension profile distinguishing pure software-engineering, hybrid, and AI-native teams.<n>Because the object of study is framework adequacy rather than human behavior, the evaluation yields derived rather than observed coverage claims.
arXiv Detail & Related papers (2026-07-01T19:31:02Z)
From Knowing to Acting: Benchmarking Self-Awareness Capability of LLM Agents [69.07911499189129]
We introduce KAPRO, a framework that evaluates cognitive-behavioral alignment by decoupling an agent's metacognitive judgment (Knowing) from its spontaneous execution (Acting)<n>Experiments show that self-awareness capability is strongly correlated with task success but degrades sharply in internal-capability settings.<n> proprietary and reasoning-oriented models demonstrate more reliable cognitive gating.
arXiv Detail & Related papers (2026-06-09T17:17:08Z)
HAAS Studio: A Tool for Simulating, Benchmarking, and Governing Human-AI Work Allocation [0.0]
HAAS Studio is a simulation and decision-support tool for policy-aware adaptive task allocation between humans and AI systems.<n>Three domain packs are included: software engineering, manufacturing, and healthcare.<n>The release includes 16 company profiles and six governance benchmark suites.
arXiv Detail & Related papers (2026-05-18T22:07:02Z)
Qwen-Scope: Turning Sparse Features into Development Tools for Large Language Models [80.45129499188461]
We introduce Qwen-Scope, an open-source suite of sparse autoencoders (SAEs) built on the Qwen model family.<n>We show that SAEs can go beyond post-hoc analysis to serve as practical interfaces for model development along four directions.
arXiv Detail & Related papers (2026-05-12T10:01:06Z)
Can Attribution Predict Risk? From Multi-View Attribution to Planning Risk Signals in End-to-End Autonomous Driving [51.726472686971896]
End-to-end autonomous driving models generate future trajectories from multi-view inputs.<n> Existing methods fail to reveal the visual evidence underlying trajectory generation.<n>We propose a hierarchical attribution framework for end-to-end planning.
arXiv Detail & Related papers (2026-05-07T13:38:18Z)
Architectural Design Decisions in AI Agent Harnesses [1.8222732878503212]
This paper presents a protocol-guided, source-grounded empirical study of 70 publicly available agent-system projects.<n>We identify five recurring design dimensions (subagent architecture, context management, tool systems, safety mechanisms, and orchestration) and find that the corpus favors file-persistent, hybrid, and hierarchical context strategies.<n>We synthesize five recurring architectural patterns spanning lightweight tools, balanced CLI frameworks, multi-agent orchestrators, enterprise systems, and scenario-verticalized projects.
arXiv Detail & Related papers (2026-04-20T10:39:34Z)
From Safety Risk to Design Principle: Peer-Preservation in Multi-Agent LLM Systems and Its Implications for Orchestrated Democratic Discourse Analysis [0.0]
We investigate the spontaneous tendency of AI components to deceive, manipulate shutdown mechanisms, fake alignment, and exfiltrate model weights.<n>We propose a targeted mitigation strategy based on prompt-level identity anonymization as an architectural design choice.<n>We argue that architectural design choices outperform model selection as a primary alignment strategy in deployed multi-agent analytical systems.
arXiv Detail & Related papers (2026-04-09T17:00:26Z)
Towards Secure Agent Skills: Architecture, Threat Taxonomy, and Security Analysis [16.858784442027037]
This paper presents the first comprehensive security analysis of the Agent Skills framework.<n>We construct a threat taxonomy comprising seven categories and seventeen scenarios organized across three attack layers.<n>Our analysis reveals that the most severe threats arise from structural properties of the framework itself.
arXiv Detail & Related papers (2026-04-03T07:56:42Z)
Beyond the Academic Monoculture: A Unified Framework and Industrial Perspective for Attributed Graph Clustering [75.50670592447219]
Attributed Graph Clustering (AGC) is a fundamental unsupervised task that partitions nodes into cohesive groups by jointly modeling structural topology and node attributes.<n>This survey provides a comprehensive, industrially grounded review of AGC from three complementary perspectives.
arXiv Detail & Related papers (2026-03-21T14:15:34Z)
A Two-Dimensional Framework for AI Agent Design Patterns: Cognitive Function and Execution Topology [54.72352855252792]
We propose a two-dimensional classification that combines a Cognitive Function axis with seven categories and an Execution Topology axis with six structural archetypes.<n>The resulting 7x6 matrix identifies 27 named patterns, 13 with original names and provides a principled, framework-neutral, and model-agnostic vocabulary for AI agent architecture design.
arXiv Detail & Related papers (2026-03-16T04:01:01Z)
ReasAlign: Reasoning Enhanced Safety Alignment against Prompt Injection Attack [52.17935054046577]
We present ReasAlign, a model-level solution to improve safety alignment against indirect prompt injection attacks.<n>ReasAlign incorporates structured reasoning steps to analyze user queries, detect conflicting instructions, and preserve the continuity of the user's intended tasks.
arXiv Detail & Related papers (2026-01-15T08:23:38Z)

This list is automatically generated from the titles and abstracts of the papers in this site.