Organizational Memory for Agentic Business Process Execution
This work addresses the scalability and consistency challenges of encoding procedural knowledge for LLM agents in enterprise settings, but the contribution is incremental as it applies known concepts (shared knowledge base) to a specific domain.
The paper identifies the problem of LLM-based agents lacking organization-specific knowledge for reliable business process execution, leading to knowledge silos and inconsistent updates. It proposes an organizational memory architecture and demonstrates its effectiveness in a procurement scenario proof-of-concept.
LLM-based agents offer new opportunities for automating business process execution beyond the limits of rule-based systems. However, general-purpose LLMs lack the organization-specific knowledge required for reliable execution, which is typically fragmented across human-oriented artifacts such as policies, process models, and standard operating procedures. While such knowledge can technically be encoded in individual prompts or agent-specific retrieval setups, this approach does not scale in enterprises, as it gives rise to knowledge silos and rule duplicates, and makes consistent updates and learning across agents difficult. We argue that this calls for an organizational memory for agentic business process execution: a shared, governed, and agent-consumable reference layer of evolving organization-specific procedural knowledge about how work should be executed. We derive requirements for such a memory, propose an architecture for its curation and consumption, and demonstrate its effectiveness in a proof-of-concept based on a procurement scenario.