Organizational Memory for Agentic Business Process Execution
Quick Answer
The paper proposes an organizational memory for LLM-based agents to enhance business process execution by addressing knowledge fragmentation.
Quick Take
It outlines an architecture for curating organization-specific procedural knowledge, demonstrating its effectiveness in a procurement scenario.
Key Points
- -based agents can automate business processes beyond rule-based systems.
- Current general-purpose LLMs lack organization-specific knowledge for reliable execution.
- Knowledge silos hinder consistent updates and learning across agents.
- The proposed architecture serves as a shared reference layer for procedural knowledge.
- A proof-of-concept demonstrates effectiveness in a procurement scenario.
Paper Resources
📖 Reader Mode
~2 min readAbstract: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.
| Subjects: | Artificial Intelligence (cs.AI); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2607.03228 [cs.AI] |
| (or arXiv:2607.03228v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.03228 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Lukas Kirchdorfer [view email]
[v1]
Fri, 3 Jul 2026 11:40:10 UTC (1,118 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.