Picture for Dehai Zhao

Dehai Zhao

An Evaluation-Driven Approach to Designing LLM Agents: Process and Architecture

Add code
Nov 21, 2024
Viaarxiv icon

Towards AI-Safety-by-Design: A Taxonomy of Runtime Guardrails in Foundation Model based Systems

Add code
Aug 05, 2024
Figure 1 for Towards AI-Safety-by-Design: A Taxonomy of Runtime Guardrails in Foundation Model based Systems
Figure 2 for Towards AI-Safety-by-Design: A Taxonomy of Runtime Guardrails in Foundation Model based Systems
Figure 3 for Towards AI-Safety-by-Design: A Taxonomy of Runtime Guardrails in Foundation Model based Systems
Figure 4 for Towards AI-Safety-by-Design: A Taxonomy of Runtime Guardrails in Foundation Model based Systems
Viaarxiv icon

Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents

Add code
May 16, 2024
Figure 1 for Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents
Figure 2 for Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents
Figure 3 for Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents
Figure 4 for Agent Design Pattern Catalogue: A Collection of Architectural Patterns for Foundation Model based Agents
Viaarxiv icon