SpecMap: Hierarchical LLM Agent for Datasheet-to-Code Traceability Link Recovery in Systems Engineering

2026-01-16

AI Summary

This work addresses the challenge of establishing efficient and precise traceability links between data sheets and low-level C/C++ code—such as macros, registers, and structs—in embedded systems, where manual mapping is prohibitively costly. To overcome the limitations of traditional lexical matching approaches, the authors propose a hierarchical traceability framework powered by large language models (LLMs), which performs repository-level structural inference, file-level relevance assessment, and symbol-level fine-grained alignment in sequence. This approach significantly enhances both semantic and structural consistency while drastically reducing computational overhead. Evaluated on multiple open-source embedded projects, the method achieves a 73.3% file-mapping accuracy, alongside an 84% reduction in LLM token consumption and approximately 80% decrease in end-to-end runtime.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Cognitive Modeling & Cognitive Systems: Conceptual Inference and Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Establishing precise traceability between embedded systems datasheets and their corresponding code implementations remains a fundamental challenge in systems engineering, particularly for low-level software where manual mapping between specification documents and large code repositories is infeasible. Existing Traceability Link Recovery approaches primarily rely on lexical similarity and information retrieval techniques, which struggle to capture the semantic, structural, and symbol level relationships prevalent in embedded systems software. We present a hierarchical datasheet-to-code mapping methodology that employs large language models for semantic analysis while explicitly structuring the traceability process across multiple abstraction levels. Rather than performing direct specification-to-code matching, the proposed approach progressively narrows the search space through repository-level structure inference, file-level relevance estimation, and fine-grained symbollevel alignment. The method extends beyond function-centric mapping by explicitly covering macros, structs, constants, configuration parameters, and register definitions commonly found in systems-level C/C++ codebases. We evaluate the approach on multiple open-source embedded systems repositories using manually curated datasheet-to-code ground truth. Experimental results show substantial improvements over traditional information-retrieval-based baselines, achieving up to 73.3% file mapping accuracy. We significantly reduce computational overhead, lowering total LLM token consumption by 84% and end-to-end runtime by approximately 80%. This methodology supports automated analysis of large embedded software systems and enables downstream applications such as training data generation for systems-aware machine learning models, standards compliance verification, and large-scale specification coverage analysis.

Problem

• traceability link recovery
• datasheet-to-code mapping
• embedded systems
• semantic analysis
• systems engineering

Innovation

• traceability link recovery
• hierarchical LLM agent
• datasheet-to-code mapping
• embedded systems
• semantic analysis