GenAI-Driven Approach to RISC-V Supply Chain Exploration

TL;DR

This paper introduces an LLM- and VLM-powered workflow for RISC-V supply chain analysis, combining multimodal data understanding with formal modeling to improve resilience assessment and decision-making.

Contribution

It presents a novel integrated approach that leverages large language and vision models with model-driven engineering for comprehensive supply chain analysis.

Findings

Effective extraction of supply chain entities from multimodal data

Formal validation of dependencies and bottleneck detection demonstrated

Enhanced transparency and decision support in RISC-V ecosystem scenarios

Abstract

This paper presents an LLM-empowered workflow for RISC-V supply chain analysis, integrating Vision-Language Models (VLMs) and Model-Driven Engineering (MDE) to enable comprehensive, multimodal data-driven insights. The proposed approach addresses the challenges of heterogeneous and unstructured supply chain data by leveraging LLMs for textual understanding and VLMs for extracting information from visual artifacts such as diagrams, tables, and scanned documents. These models collaboratively identify key entities and relationships, which are then organized into a knowledge graph representing supply chain components and their interdependencies. For analytical reasoning, the workflow incorporates MDE techniques and constraint-based modeling to enable formal validation of dependencies, detection of bottlenecks, and assessment of risks. The synergy between LLM- and VLM-based semantic understanding and MDE-based formal analysis supports both exploratory and systematic evaluation of supply chain resilience. A human-in-the-loop mechanism further enables interactive querying and expert validation. The approach is evaluated in RISC-V ecosystem scenarios, demonstrating its effectiveness in generating actionable insights, enhancing transparency, and supporting decision-making in complex semiconductor supply chains.