# Beyond Control-Flow: Integrating the Resource Perspective into Multi-Collaborative Process Modeling from Text

arXiv: https://arxiv.org/abs/2605.24546 · HTML: https://mlsanity.com/paper/2605.24546/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 9 of its 22 references that are in the map.
- First posted on arXiv 23 May 2026.

## Builds on (most cited first, 9 of 9)

- [Towards Mitigating Hallucination in Large Language Models via Self-Reflection](https://mlsanity.com/paper/2310.06271/) (2023)
- [Process Modeling With Large Language Models](https://mlsanity.com/paper/2403.07541/) (2024)
- [Evaluating Large Language Models on Business Process Modeling: Framework, Benchmark, and Self-Improvement Analysis](https://mlsanity.com/paper/2412.00023/) (2024)
- [ProMoAI: Process Modeling with Generative AI](https://mlsanity.com/paper/2403.04327/) (2024)
- [SAP Signavio Academic Models: A Large Process Model Dataset](https://mlsanity.com/paper/2208.12223/) (2022)
- [MAO: A Framework for Process Model Generation with Multi-Agent Orchestration](https://mlsanity.com/paper/2408.01916/) (2024)
- [BPMN Assistant: An LLM-Based Approach to Business Process Modeling](https://mlsanity.com/paper/2509.24592/) (2025)
- [Unlocking Non-Block-Structured Decisions: Inductive Mining with Choice Graphs](https://mlsanity.com/paper/2505.07052/) (2025)
- [Knowledge-Driven Hallucination in Large Language Models: An Empirical Study on Process Modeling](https://mlsanity.com/paper/2509.15336/) (2025)

## Abstract (arXiv)

Process modeling is a sub-domain of Business Process Management (BPM) focused on the translation of process artifacts into formal models. This task traditionally requires extensive human input and domain expertise in both BPM notations and the specific business context. While Large Language Models (LLMs) can now automate much of this manual work, current text-to-model approaches focus predominantly on the control-flow perspective-ordering activities without considering the collaborative aspect of the processes. In this paper, we introduce a resource-aware generation pipeline that produces formal BPMN 2.0 collaboration diagrams from natural-language descriptions. Rather than solely prompting an LLM for raw XML, we describe a compact, executable intermediate language with mandatory resource details defining both the organization (pool) and the role (lane). Cross-organization dependencies are materialized using the standard formal notation for such interactions-message events-while an orthogonal layout routine automatically handles the spatial arrangement of elements within pools and lanes. Experiments on ten business processes with nine LLMs show strong resource discovery while preserving control-flow quality and adding only marginal runtime overhead. This approach moves generative modeling toward a more comprehensive, multi-collaborative representation of business operations.