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

TL;DR

This paper introduces SpecMap, a hierarchical LLM-based approach for accurate and efficient traceability link recovery between datasheets and code in embedded systems, improving over traditional methods.

Contribution

It presents a novel hierarchical methodology leveraging large language models for semantic and structural analysis across multiple abstraction levels in embedded systems.

Findings

Achieves up to 73.3% file mapping accuracy.

Reduces LLM token consumption by 84%.

Cuts end-to-end runtime by approximately 80%.

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.