Niek Tax

Unbiased Prevalence Estimation with Multicalibrated LLMs

Fridolin Linder, Thomas Leeper, Daniel Haimovich, et al.

Agentic Business Process Management: A Research Manifesto

Diego Calvanese, Angelo Casciani, Giuseppe De Giacomo, et al.

This paper proposes Agentic Business Process Management (APM), a new approach that combines traditional business process management with autonomous AI agents. Rather than just automating workflows, APM allows software and human agents to work intelligently within organizational processes by being aware of goals, explaining their decisions, and adapting their behavior. The paper outlines four key capabilities these agents need—constrained autonomy, explainability, conversational interaction, and self-improvement—to ensure they stay aligned with organizational objectives while operating proactively.