Design and Implementation of Agentic Orchestrations and Orchestration of Agents
This work offers a structured approach for designing and evaluating orchestration of LLM-based agents, addressing a need for balancing autonomy with robustness in business process management.
The paper proposes a classification framework for agentic orchestration options in AI agent systems, providing qualitative decision criteria and quantitative metrics for assessing realizations, demonstrated through a predictive light sensing scenario.
Agentic Business Process Management has gained momentum recently. The prospect is that the autonomy of AI agents, i.e., predominantly LLM-based agents, can be balanced with a certain level of robustness, tractability, and traceability through a combination with process technology. In this paper, we provide a classification framework for agentic orchestration options along properties such as task specificity, traceability and tractability, autonomy and reactivity, and correctness assurance and present qualitative decision criteria for realizations of different scenarios. We also provide metrics for the quantitative assessment of realization properties and show them through different agentic implementations of a predictive light sensing scenario. Altogether, this work aims at providing properties, criteria, and metrics for the design and implementation of agentic orchestrations and orchestration of agents.