Exploring Network-Knowledge Graph Duality: A Case Study in Agentic Supply Chain Risk Analysis
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2025
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866918249417932800 |
|---|---|
| author | Heus, Evan Bookstaber, Rick Sharma, Dhruv |
| author_facet | Heus, Evan Bookstaber, Rick Sharma, Dhruv |
| contents | Large Language Models (LLMs) struggle with the complex, multi-modal, and network-native data underlying financial risk. Standard Retrieval-Augmented Generation (RAG) oversimplifies relationships, while specialist models are costly and static. We address this gap with an LLM-centric agent framework for supply chain risk analysis. Our core contribution is to exploit the inherent duality between networks and knowledge graphs (KG). We treat the supply chain network as a KG, allowing us to use structural network science principles for retrieval. A graph traverser, guided by network centrality scores, efficiently extracts the most economically salient risk paths. An agentic architecture orchestrates this graph retrieval alongside data from numerical factor tables and news streams. Crucially, it employs novel ``context shells'' -- descriptive templates that embed raw figures in natural language -- to make quantitative data fully intelligible to the LLM. This lightweight approach enables the model to generate concise, explainable, and context-rich risk narratives in real-time without costly fine-tuning or a dedicated graph database. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2510_01115 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Exploring Network-Knowledge Graph Duality: A Case Study in Agentic Supply Chain Risk Analysis Heus, Evan Bookstaber, Rick Sharma, Dhruv Artificial Intelligence Multiagent Systems Theoretical Economics Physics and Society Large Language Models (LLMs) struggle with the complex, multi-modal, and network-native data underlying financial risk. Standard Retrieval-Augmented Generation (RAG) oversimplifies relationships, while specialist models are costly and static. We address this gap with an LLM-centric agent framework for supply chain risk analysis. Our core contribution is to exploit the inherent duality between networks and knowledge graphs (KG). We treat the supply chain network as a KG, allowing us to use structural network science principles for retrieval. A graph traverser, guided by network centrality scores, efficiently extracts the most economically salient risk paths. An agentic architecture orchestrates this graph retrieval alongside data from numerical factor tables and news streams. Crucially, it employs novel ``context shells'' -- descriptive templates that embed raw figures in natural language -- to make quantitative data fully intelligible to the LLM. This lightweight approach enables the model to generate concise, explainable, and context-rich risk narratives in real-time without costly fine-tuning or a dedicated graph database. |
| title | Exploring Network-Knowledge Graph Duality: A Case Study in Agentic Supply Chain Risk Analysis |
| topic | Artificial Intelligence Multiagent Systems Theoretical Economics Physics and Society |
| url | https://arxiv.org/abs/2510.01115 |