{"total":64,"rows":[{"id":"2309.07544","title":"VerilogEval: Evaluating Large Language Models for Verilog Code Generation","created":"2023-09-14","cited_by_count":252,"area":null},{"id":"2403.08937","title":"Bugs in Large Language Models Generated Code: An Empirical Study","created":"2024-03-13","cited_by_count":60,"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":"2308.04451","title":"Vulnerabilities in AI Code Generators: Exploring Targeted Data Poisoning Attacks","created":"2023-08-04","cited_by_count":33,"area":"safety"},{"id":"2404.14901","title":"Beyond Code Generation: An Observational Study of ChatGPT Usage in Software Engineering Practice","created":"2024-04-23","cited_by_count":25,"area":null},{"id":"2511.12884","title":"Agent READMEs: An Empirical Study of Context Files for Agentic Coding","created":"2025-11-17","cited_by_count":23,"area":"agents"},{"id":"2406.19783","title":"NLPerturbator: Studying the Robustness of Code LLMs to Natural Language Variations","created":"2024-06-28","cited_by_count":20,"area":null},{"id":"2309.04142","title":"Trustworthy and Synergistic Artificial Intelligence for Software Engineering: Vision and Roadmaps","created":"2023-09-08","cited_by_count":19,"area":null},{"id":"2306.14583","title":"Exploring the Robustness of Large Language Models for Solving Programming Problems","created":"2023-06-26","cited_by_count":16,"area":null},{"id":"2504.14119","title":"CodeCrash: Exposing LLM Fragility to Misleading Natural Language in Code Reasoning","created":"2025-04-19","cited_by_count":14,"area":"lr"},{"id":"2412.18260","title":"Investigating Large Language Models for Code Vulnerability Detection: An Experimental Study","created":"2024-12-24","cited_by_count":12,"area":null},{"id":"2310.17903","title":"Pitfalls in Language Models for Code Intelligence: A Taxonomy and Survey","created":"2023-10-27","cited_by_count":9,"area":null},{"id":"2312.14856","title":"Turbulence: Systematically and Automatically Testing Instruction-Tuned Large Language Models for Code","created":"2023-12-22","cited_by_count":9,"area":null},{"id":"2404.14871","title":"Exploring Human-AI Collaboration in Agile: Customised LLM Meeting Assistants","created":"2024-04-23","cited_by_count":9,"area":null},{"id":"2504.01986","title":"TuRTLe: A Unified Evaluation of LLMs for RTL Generation","created":"2025-03-31","cited_by_count":9,"area":null},{"id":"2401.15545","title":"PPM: Automated Generation of Diverse Programming Problems for Benchmarking Code Generation Models","created":"2024-01-28","cited_by_count":8,"area":null},{"id":"2503.02296","title":"Memorize or Generalize? Evaluating LLM Code Generation with Code Rewriting","created":"2025-03-04","cited_by_count":7,"area":null},{"id":"2402.08430","title":"Analyzing Prompt Influence on Automated Method Generation: An Empirical Study with Copilot","created":"2024-02-13","cited_by_count":6,"area":null},{"id":"2403.12671","title":"Enhancing Security of AI-Based Code Synthesis with GitHub Copilot via Cheap and Efficient Prompt-Engineering","created":"2024-03-19","cited_by_count":6,"area":null},{"id":"2506.11059","title":"CodeMirage: A Multi-Lingual Benchmark for Detecting AI-Generated and Paraphrased Source Code from Production-Level LLMs","created":"2025-05-27","cited_by_count":6,"area":null},{"id":"2312.04986","title":"Out of Context: How important is Local Context in Neural Program Repair?","created":"2023-12-08","cited_by_count":5,"area":null},{"id":"2312.15614","title":"A Comprehensive Evaluation of Parameter-Efficient Fine-Tuning on Software Engineering Tasks","created":"2023-12-25","cited_by_count":5,"area":null},{"id":"2503.06195","title":"Human-AI Experience in Integrated Development Environments: A Systematic Literature Review","created":"2025-03-08","cited_by_count":5,"area":null},{"id":"2308.02955","title":"An Empirical Study of AI-based Smart Contract Creation","created":"2023-08-05","cited_by_count":4,"area":null},{"id":"2407.11019","title":"Efficacy of Various Large Language Models in Generating Smart Contracts","created":"2024-06-28","cited_by_count":4,"area":null},{"id":"2502.02368","title":"Evaluating the Effectiveness of LLMs in Fixing Maintainability Issues in Real-World Projects","created":"2025-02-04","cited_by_count":4,"area":null},{"id":"2503.12217","title":"TFHE-Coder: Evaluating LLM-agentic Fully Homomorphic Encryption Code Generation","created":"2025-03-15","cited_by_count":4,"area":"agents"},{"id":"2510.10460","title":"Understanding and Bridging the Planner-Coder Gap: A Systematic Study on the Robustness of Multi-Agent Systems for Code Generation","created":"2025-10-12","cited_by_count":4,"area":"agents"},{"id":"2604.07727","title":"TrajGuard: Streaming Hidden-state Trajectory Detection for Decoding-time Jailbreak Defense","created":"2026-04-09","cited_by_count":4,"area":"safety"},{"id":"2605.14675","title":"Agentic AI in Industry: Adoption Level and Deployment Barriers","created":"2026-05-14","cited_by_count":4,"area":"agents"},{"id":"2306.05079","title":"Enhancing Robustness of AI Offensive Code Generators via Data Augmentation","created":"2023-06-08","cited_by_count":3,"area":null},{"id":"2405.13932","title":"Chain of Targeted Verification Questions to Improve the Reliability of Code Generated by LLMs","created":"2024-05-22","cited_by_count":3,"area":null},{"id":"2406.07683","title":"Impact of AI-tooling on the Engineering Workspace","created":"2024-06-11","cited_by_count":3,"area":null},{"id":"2407.21227","title":"TaskEval: Assessing Difficulty of Code Generation Tasks for Large Language Models","created":"2024-07-30","cited_by_count":3,"area":null},{"id":"2408.02402","title":"Enhancing AI-based Generation of Software Exploits with Contextual Information","created":"2024-08-05","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":"2412.10953","title":"Optimizing AI-Assisted Code Generation","created":"2024-12-14","cited_by_count":2,"area":null},{"id":"2604.24703","title":"Defective Task Descriptions in LLM-Based Code Generation: Detection and Analysis","created":"2026-04-27","cited_by_count":2,"area":null},{"id":"2608.18389","title":"A Jagged Frontier: Evaluating Robustness of Code Agents to Semantics-Preserving Transformations","created":"2026-08-18","cited_by_count":2,"area":"agents"},{"id":"2406.10141","title":"The Rise and Fall(?) of Software Engineering","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2502.13199","title":"The Role of GitHub Copilot on Software Development: A Perspective on Productivity, Security, Best Practices and Future Directions","created":"2025-02-18","cited_by_count":1,"area":null},{"id":"2510.20721","title":"User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios","created":"2025-10-23","cited_by_count":1,"area":null},{"id":"2603.10969","title":"TOSSS: a CVE-based Software Security Benchmark for Large Language Models","created":"2026-03-11","cited_by_count":1,"area":null},{"id":"2603.13036","title":"Interrogating Design Homogenization in Web Vibe Coding","created":"2026-03-13","cited_by_count":1,"area":null},{"id":"2604.23135","title":"Characterizing Paraphrase-Induced Failures in Lean 4 Autoformalization","created":"2026-04-25","cited_by_count":1,"area":null},{"id":"2308.09721","title":"A new solution and concrete implementation steps for Artificial General Intelligence","created":"2023-08-12","cited_by_count":0,"area":"wm"},{"id":"2411.15470","title":"A Preliminary Study of Multilingual Code Language Models for Code Generation Task Using Translated Benchmarks","created":"2024-11-23","cited_by_count":0,"area":null},{"id":"2506.02791","title":"Contamination Means Overestimation? A Fine-Grained Empirical Study in Code Intelligence","created":"2025-06-03","cited_by_count":0,"area":null},{"id":"2512.02567","title":"Feedback Loops and Code Perturbations in LLM-based Software Engineering: A Case Study on a C-to-Rust Translation System","created":"2025-12-02","cited_by_count":0,"area":null},{"id":"2512.05242","title":"Learning to Code with Context: A Study-Based Approach","created":"2025-12-04","cited_by_count":0,"area":null},{"id":"2512.15003","title":"SeBERTis: A Framework for Producing Classifiers of Security-Related Issue Reports","created":"2025-12-17","cited_by_count":0,"area":null},{"id":"2601.17604","title":"Human-Aligned Enhancement of Programming Answers with LLMs Guided by User Feedback","created":"2026-01-24","cited_by_count":0,"area":null},{"id":"2602.10808","title":"PELLI: Framework to effectively integrate LLMs for quality software generation","created":"2026-02-11","cited_by_count":0,"area":null},{"id":"2602.15350","title":"Fine-Tuning LLMs to Generate Economical and Reliable Actions for the Power Grid","created":"2026-02-17","cited_by_count":0,"area":null},{"id":"2602.18800","title":"Operational Robustness of LLMs on Code Generation","created":"2026-02-21","cited_by_count":0,"area":null},{"id":"2603.12712","title":"Design-Specification Tiling for ICL-based CAD Code Generation","created":"2026-03-13","cited_by_count":0,"area":null},{"id":"2606.13802","title":"A Benchmark and Framework for Evaluating Next Action Predictions in Spreadsheets","created":"2026-06-11","cited_by_count":0,"area":null},{"id":"2607.14181","title":"Quantize with Confidence? An Empirical Study of Quantization for Code Generation","created":"2026-07-15","cited_by_count":0,"area":null},{"id":"2607.14816","title":"Large Language Models for Code Generation from Multilingual Prompts: A Curated Benchmark and a Study on Code Quality","created":"2026-07-16","cited_by_count":0,"area":null},{"id":"2607.18057","title":"Test Coverage Analysis of Agentic Pull Requests","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2608.12771","title":"Memorization Diagnostics for Code LLMs Should be Scale-Aware","created":"2026-08-13","cited_by_count":0,"area":null},{"id":"2609.00568","title":"WiseSpec: Requirements-Driven Agents for Code Generation","created":"2026-09-01","cited_by_count":0,"area":"agents"},{"id":"2609.07434","title":"CIT-CAD: Constraint Intent Tree-based CAD Code Generation and Verification","created":"2026-09-07","cited_by_count":0,"area":null},{"id":"2609.09798","title":"CS-Guard: Benchmarking LLM Guardrails for Code Generation Security","created":"2026-09-09","cited_by_count":0,"area":"safety"}],"next_cursor":null}