Agentic Insight Generation in VSM Simulations
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917406488657920 |
|---|---|
| author | Selak, Micha Krechel, Dirk Ulges, Adrian Spieckermann, Sven Stoehr, Niklas Loehr, Andreas |
| author_facet | Selak, Micha Krechel, Dirk Ulges, Adrian Spieckermann, Sven Stoehr, Niklas Loehr, Andreas |
| contents | Extracting actionable insights from complex value stream map simulations can be challenging, time-consuming, and error-prone. Recent advances in large language models offer new avenues to support users with this task. While existing approaches excel at processing raw data to gain information, they are structurally unfit to pick up on subtle situational differences needed to distinguish similar data sources in this domain. To address this issue, we propose a decoupled, two-step agentic architecture. By separating orchestration from data analysis, the system leverages progressive data discovery infused with domain expert knowledge. This architecture allows the orchestration to intelligently select data sources and perform multi-hop reasoning across data structures while maintaining a slim internal context. Results from multiple state-of-the-art large language models demonstrate the framework's viability: with top-tier models achieving accuracies of up to 86% and demonstrating high robustness across evaluation runs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_12421 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | Agentic Insight Generation in VSM Simulations Selak, Micha Krechel, Dirk Ulges, Adrian Spieckermann, Sven Stoehr, Niklas Loehr, Andreas Computation and Language Extracting actionable insights from complex value stream map simulations can be challenging, time-consuming, and error-prone. Recent advances in large language models offer new avenues to support users with this task. While existing approaches excel at processing raw data to gain information, they are structurally unfit to pick up on subtle situational differences needed to distinguish similar data sources in this domain. To address this issue, we propose a decoupled, two-step agentic architecture. By separating orchestration from data analysis, the system leverages progressive data discovery infused with domain expert knowledge. This architecture allows the orchestration to intelligently select data sources and perform multi-hop reasoning across data structures while maintaining a slim internal context. Results from multiple state-of-the-art large language models demonstrate the framework's viability: with top-tier models achieving accuracies of up to 86% and demonstrating high robustness across evaluation runs. |
| title | Agentic Insight Generation in VSM Simulations |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.12421 |