{"total":16,"rows":[{"id":"2502.06193","title":"Can LLMs Replace Human Evaluators? An Empirical Study of LLM-as-a-Judge in Software Engineering","created":"2025-02-10","cited_by_count":67,"area":null},{"id":"2502.17521","title":"Recent Advances in Large Langauge Model Benchmarks against Data Contamination: From Static to Dynamic Evaluation","created":"2025-02-23","cited_by_count":38,"area":null},{"id":"2505.16901","title":"Code Graph Model (CGM): A Graph-Integrated Large Language Model for Repository-Level Software Engineering Tasks","created":"2025-05-22","cited_by_count":27,"area":null},{"id":"2505.16975","title":"SWE-Dev: Evaluating and Training Autonomous Feature-Driven Software Development","created":"2025-05-22","cited_by_count":16,"area":null},{"id":"2412.18573","title":"Top General Performance = Top Domain Performance? DomainCodeBench: A Multi-domain Code Generation Benchmark","created":"2024-12-24","cited_by_count":13,"area":null},{"id":"2409.15204","title":"RAMBO: Enhancing RAG-based Repository-Level Method Body Completion","created":"2024-09-23","cited_by_count":10,"area":null},{"id":"2504.20964","title":"OSVBench: Benchmarking LLMs on Specification Generation Tasks for Operating System Verification","created":"2025-04-29","cited_by_count":8,"area":null},{"id":"2508.14727","title":"Assessing the Quality and Security of AI-Generated Code: A Quantitative Analysis","created":"2025-08-20","cited_by_count":7,"area":null},{"id":"2505.12331","title":"OSS-Bench: Benchmark Generator for Coding LLMs","created":"2025-05-18","cited_by_count":6,"area":null},{"id":"2506.13824","title":"MLDebugging: Towards Benchmarking Code Debugging Across Multi-Library Scenarios","created":"2025-06-15","cited_by_count":3,"area":null},{"id":"2506.22776","title":"Smaller = Weaker? Benchmarking Robustness of Quantized LLMs in Code Generation","created":"2025-06-28","cited_by_count":3,"area":null},{"id":"2511.18842","title":"Optimizing LLM Code Suggestions: Feedback-Driven Timing with Lightweight State Bounds","created":"2025-11-24","cited_by_count":2,"area":null},{"id":"2608.23961","title":"Evaluating Language Models on Cross-Language Code Functional Equivalence","created":"2026-08-25","cited_by_count":2,"area":null},{"id":"2512.20159","title":"Benchmarking Code LLM-as-a-Judge via Constrained Perturbation and Calibration","created":"2025-12-23","cited_by_count":1,"area":null},{"id":"2601.04540","title":"AdaptEval: A Benchmark for Evaluating Large Language Models on Code Snippet Adaptation","created":"2026-01-08","cited_by_count":1,"area":null},{"id":"2507.23178","title":"AutoBridge: Automating Smart Device Integration with Centralized Platform","created":"2025-07-31","cited_by_count":0,"area":null}],"next_cursor":null}