An empirical study of 70 AI agent systems identifies five design dimensions and five common architectural patterns in their supporting infrastructure.
MCP Safety Audit: LLMs with the Model Context Protocol Allow Major Security Exploits
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.AI 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Architectural Design Decisions in AI Agent Harnesses
An empirical study of 70 AI agent systems identifies five design dimensions and five common architectural patterns in their supporting infrastructure.