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

Why we picked it

This week, we will walk through and discuss of the paper: R2Code: A Self-Reflective LLM Framework for Requirements-to-Code Traceability [https://arxiv.org/pdf/2604.22432] **Abstract of the Paper:** 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