Organizational Memory for Agentic Business Process Execution
Lukas Kirchdorfer, Adrian Rebmann, Christian Warmuth, Timotheus Kampik, Theiss Heilker, Gregor Berg
Why It Matters
What makes this one worth your time
This work is relevant for AI engineers and researchers interested in improving the scalability and consistency of LLM-based business process automation in enterprises.
The paper introduces a shared organizational memory for LLM-based business process execution.
Summary
The paper proposes an organizational memory framework for business process execution using LLM-based agents, addressing the limitations of fragmented organization-specific knowledge in rule-based systems. It outlines requirements, suggests an architecture, and demonstrates a proof-of-concept in a procurement scenario.
Key contributions
- Proposal of an organizational memory framework for agentic business process execution.
- Derivation of requirements for the proposed memory system.
- Proof-of-concept demonstration in a procurement scenario.
Notable insights
- The concept of a shared organizational memory to prevent knowledge silos and rule duplicates.
- An architecture for curating and consuming organization-specific procedural knowledge.
Possible limitations
- Not stated in the abstract
Abstract
arXiv:2607.03228v1 Announce Type: new Abstract: 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.