{"total":24,"rows":[{"id":"2412.21199","title":"HumanEval Pro and MBPP Pro: Evaluating Large Language Models on Self-invoking Code Generation","created":"2024-12-30","cited_by_count":39,"area":null},{"id":"2509.11252","title":"Exploring the Potential of Diffusion Large Language Models in Code Generation","created":"2025-09-14","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":"2503.07358","title":"RepoST: Scalable Repository-Level Coding Environment Construction with Sandbox Testing","created":"2025-03-10","cited_by_count":13,"area":null},{"id":"2508.14104","title":"You Don't Know Until You Click:Automated GUI Testing for Production-Ready Software Evaluation","created":"2025-08-17","cited_by_count":12,"area":null},{"id":"2503.16922","title":"RustEvo^2: An Evolving Benchmark for API Evolution in LLM-based Rust Code Generation","created":"2025-03-21","cited_by_count":10,"area":null},{"id":"2511.05931","title":"Self-Abstraction from Grounded Experience for Plan-Guided Policy Refinement","created":"2025-11-08","cited_by_count":9,"area":null},{"id":"2603.11863","title":"CreativeBench: Benchmarking and Enhancing Machine Creativity via Self-Evolving Challenges","created":"2026-03-12","cited_by_count":9,"area":null},{"id":"2510.03999","title":"LH-Deception: Simulating and Understanding LLM Deceptive Behaviors in Long-Horizon Interactions","created":"2025-10-05","cited_by_count":7,"area":null},{"id":"2505.11480","title":"SuperCoder: Assembly Program Superoptimization with Large Language Models","created":"2025-05-16","cited_by_count":6,"area":null},{"id":"2509.04078","title":"RepoDebug: Repository-Level Multi-Task and Multi-Language Debugging Evaluation of Large Language Models","created":"2025-09-04","cited_by_count":5,"area":null},{"id":"2506.10204","title":"Code Roulette: How Prompt Variability Affects LLM Code Generation","created":"2025-06-11","cited_by_count":4,"area":null},{"id":"2604.12268","title":"CodeSpecBench: Benchmarking LLMs for Executable Behavioral Specification Generation","created":"2026-04-14","cited_by_count":4,"area":null},{"id":"2505.24715","title":"CoRet: Improved Retriever for Code Editing","created":"2025-05-30","cited_by_count":3,"area":null},{"id":"2508.07180","title":"Code2Bench: Scaling Source and Rigor for Dynamic Benchmark Construction","created":"2025-08-10","cited_by_count":3,"area":null},{"id":"2512.14018","title":"PerfCoder: Large Language Models for Interpretable Code Performance Optimization","created":"2025-12-16","cited_by_count":3,"area":null},{"id":"2505.20505","title":"Large Language Models for IT Automation Tasks: Are We There Yet?","created":"2025-05-26","cited_by_count":1,"area":null},{"id":"2603.24586","title":"Comparing Developer and LLM Biases in Code Evaluation","created":"2026-03-25","cited_by_count":1,"area":null},{"id":"2604.19750","title":"Coding with Eyes: Visual Feedback Unlocks Reliable GUI Code Generating and Debugging","created":"2026-03-14","cited_by_count":1,"area":null},{"id":"2605.05700","title":"An Empirical Study of Proactive Coding Assistants in Real-World Software Development","created":"2026-05-07","cited_by_count":1,"area":null},{"id":"2601.21070","title":"Towards Comprehensive Benchmarking Infrastructure for LLMs In Software Engineering","created":"2026-01-28","cited_by_count":0,"area":null},{"id":"2602.05780","title":"Automated Customization of LLMs for Enterprise Code Repositories Using Semantic Scopes","created":"2026-02-05","cited_by_count":0,"area":null},{"id":"2609.26480","title":"FeatLens: Feature-Guided Dynamic Code Graph Construction and Retrieval for Repository-Level Code Generation","created":"2026-09-22","cited_by_count":0,"area":null},{"id":"2609.33411","title":"MetaBench-Harness: Unlocking End-to-End Optimization of Benchmark Harnesses","created":"2026-09-27","cited_by_count":0,"area":null}],"next_cursor":null}