{"total":22,"rows":[{"id":"2402.00097","title":"Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM","created":"2024-01-31","cited_by_count":64,"area":null},{"id":"2403.16218","title":"CoverUp: Effective High Coverage Test Generation for Python","created":"2024-03-24","cited_by_count":38,"area":null},{"id":"2502.06215","title":"LessLeak-Bench: A First Investigation of Data Leakage in LLMs Across 83 Software Engineering Benchmarks","created":"2025-02-10","cited_by_count":37,"area":null},{"id":"2504.14757","title":"SWE-Synth: Synthesizing Verifiable Bug-Fix Data to Enable Large Language Models in Resolving Real-World Bugs","created":"2025-04-20","cited_by_count":22,"area":null},{"id":"2411.13323","title":"Are Large Language Models Memorizing Bug Benchmarks?","created":"2024-11-20","cited_by_count":12,"area":null},{"id":"2409.09464","title":"Measuring the Influence of Incorrect Code on Test Generation","created":"2024-09-14","cited_by_count":11,"area":null},{"id":"2402.11892","title":"Towards Reliable Evaluation of Neural Program Repair with Natural Robustness Testing","created":"2024-02-19","cited_by_count":5,"area":null},{"id":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2504.04372","title":"Assessing the Impact of Code Changes on the Fault Localizability of Large Language Models","created":"2025-04-06","cited_by_count":4,"area":null},{"id":"2510.03178","title":"When Names Disappear: Revealing What LLMs Actually Understand About Code","created":"2025-10-03","cited_by_count":4,"area":null},{"id":"2412.18750","title":"Order Matters! An Empirical Study on Large Language Models' Input Order Bias in Software Fault Localization","created":"2024-12-25","cited_by_count":3,"area":null},{"id":"2501.18005","title":"Fault Localization via Fine-tuning Large Language Models with Mutation Generated Stack Traces","created":"2025-01-29","cited_by_count":1,"area":null},{"id":"2505.05777","title":"PyResBugs: A Dataset of Residual Python Bugs for Natural Language-Driven Fault Injection","created":"2025-05-09","cited_by_count":1,"area":null},{"id":"2506.13182","title":"From Empirical Evaluation to Context-Aware Enhancement: Repairing Regression Errors with LLMs","created":"2025-06-16","cited_by_count":1,"area":null},{"id":"2601.18949","title":"Tricky$^2$: Towards a Benchmark for Evaluating Human and LLM Error Interactions","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2604.23361","title":"An Empirical Evaluation of Locally Deployed LLMs for Bug Detection in Python Code","created":"2026-04-25","cited_by_count":0,"area":null},{"id":"2606.22475","title":"All Green, Still Broken: Real-Flow Verification Lessons from an LLM-Integrated, Multi-Market Web Application","created":"2026-06-21","cited_by_count":0,"area":null},{"id":"2606.29088","title":"Diff-Based Code Corruption using LLMs for Large-Scale Bugfix Benchmarking","created":"2026-06-27","cited_by_count":0,"area":null},{"id":"2607.22880","title":"Do Coverage and Mutation Scores of LLM-Generated Test Suites Correlate with Their Effectiveness? (Replicability Study)","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2608.21107","title":"Large Language Models at the Intersection of Software Engineering and Software Security:An Evidence-Centered Structured Survey and Research Agenda","created":"2026-08-21","cited_by_count":0,"area":null},{"id":"2609.03894","title":"CROCODIL: Cross-Model Code Editing with LLMs","created":"2026-09-03","cited_by_count":0,"area":null},{"id":"2610.20038","title":"SWE-Nexus: Automated Composition of Software Engineering Tasks from Test Execution","created":"2026-10-14","cited_by_count":0,"area":null}],"next_cursor":null}