R2Code: A Self-Reflective LLM Framework for Requirements-to-Code Traceability

TL;DR

R2Code is a novel LLM-based framework that enhances requirement-to-code traceability by combining semantic alignment, self-reflection, and adaptive retrieval, achieving higher accuracy and efficiency.

Contribution

It introduces a self-reflective, multi-component framework that significantly improves trace link accuracy and reduces inference costs over existing methods.

Findings

Outperforms baselines with a 7.4% average F1 gain.

Reduces token consumption by up to 41.7%.

Effective across multiple domains and programming languages.

Abstract

Accurate requirement-to-code traceability is crucial for software maintenance. However, existing IR- and embedding-based methods are heavily dependent on lexical similarity, often yielding incomplete or inconsistent links across projects and languages and incurring high cost from long-context retrieval and prompting. This paper presents R2Code, an LLM-based semantic traceability framework designed to improve trace link accuracy while reducing inference cost. R2Code integrates three components: 1) a decomposition-enhanced Bidirectional Alignment Network (BAN) that aligns four-layer requirement semantics with corresponding code structures to support cross-level semantic matching; 2) a Self-Reflective Consistency Verification (SRCV) module that conducts explanation-guided consistency checking to calibrate link reliability; and 3) a Dynamic Context-Adaptive Retrieval (DCAR) mechanism that adjusts retrieval granularity and filters contexts using semantic-overlap weighting for efficient context utilization. Experiments on five public datasets spanning multiple domains and two programming languages demonstrate that R2Code consistently outperforms the strongest baselines, achieving an average F1 gain of 7.4%, while reducing token consumption by up to 41.7% through adaptive context control.