Towards Automated Evaluation of Multi-Turn Agentic AI Systems

Forschungsstelle

INNOSUISSE

Projektnummer

129.524 INNO-ICT

Projekttitel

Towards Automated Evaluation of Multi-Turn Agentic AI Systems

Projekttitel Englisch

Towards Automated Evaluation of Multi-Turn Agentic AI Systems

Texte zu diesem Projekt

	Deutsch	Französisch	Italienisch	Englisch
Schlüsselwörter	-	-	-
Abstract	-	-	-

Kategorie	Text
Schlüsselwörter (Englisch)	ICT, Artificial/local/extended/networked intelligence
Abstract (Englisch)	We propose an LLM-based framework for automated evaluation of multi-turn Agentic AI systems. By simulating diverse user interactions and assessing sub-task performance, it allows for an innovative approach for systematic testing, which reduces the reliance on expensive manual annotation.