iCoRe: An Iterative Correlation-Aware Retriever for Bug Reproduction Test Generation

2026-04-21

AI Summary

This work addresses the challenge of automatically generating defect-reproducing tests from issue descriptions, a task hindered by insufficient code context retrieval in existing approaches. The authors propose an iterative, relation-aware context retrieval method that explicitly models three key couplings: between source code and test cases, between semantic and function-call structures, and between retrieval and generation processes. By differentiating the retrieval requirements for these two types of code and integrating semantic information, call-graph analysis, and execution feedback into a closed-loop optimization framework, the approach significantly improves defect reproduction accuracy. Evaluated on SWT-bench Lite and TDD-bench Verified, the method achieves Fail-to-Pass rates of 42.0% and 52.8%, respectively, representing relative improvements of 19.7%–31.7% over current state-of-the-art techniques.

Technology Category

• Natural Language Processing: Code Generation / Program Synthesis from Natural Language
• Search and Optimization: Sampling/Simulation-based Search
• Constraint Satisfaction and Optimization: Satisfiability Modulo Theories

Application Category

• Search and Retrieval-Augmented AI: Web evaluation methodologies and metrics
• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Automatically generating bug reproduction tests (BRT) from issue descriptions is crucial for software maintenance. LLM-based approaches have shown great potential for this task. Their effectiveness heavily relies on retrieving high-quality context from the codebase. The retrieval phase of existing approaches relies on either traditional methods like BM25 or LLM-driven strategies. LLM-based retrieval strategies typically equip an LLM with tools to autonomously explore the repository or select the most relevant files and code snippets from a provided list as context. However, these retrieval methods suffer from three key limitations: 1) They often employ a unified strategy for retrieving both source code and test cases, overlooking their distinct retrieval requirements. 2) They focus solely on semantic similarity while ignoring function call relationships, leading to irrelevant context. 3) The retrieval lacks a feedback loop from the generation phase, preventing it from refining the context based on execution results. These limitations collectively result in low-quality context, thereby hindering the accuracy of bug reproduction. To address these challenges, we propose iCoRe, an iterative, correlation-aware context retrieval approach explicitly aware of three key correlations: 1) between source code and test cases, which requires differentiated retrieval, 2) between textual semantics and function call structures for accurate relevance assessment, and 3) between the retrieval and generation phases, which enables iterative feedback and refinement. To evaluate iCoRe, we integrate it with an LLM-based BRT generator and conduct a comprehensive evaluation on the SWT-bench Lite and TDD-bench Verified benchmarks. Experimental results show that our method achieves a Fail-to-Pass rate of 42.0% and 52.8% respectively, representing 19.7%-31.7% relative improvements over existing retrieval methods.

Problem

• bug reproduction test generation
• context retrieval
• LLM-based software maintenance
• function call relationships
• retrieval-generation feedback

Innovation

• iterative retrieval
• correlation-aware
• bug reproduction test
• function call structure
• LLM-based code generation