{"total":79,"rows":[{"id":"2309.16609","title":"Qwen Technical Report","created":"2023-09-28","cited_by_count":3344,"area":null},{"id":"2406.00515","title":"A Survey on Large Language Models for Code Generation","created":"2024-06-01","cited_by_count":658,"area":null},{"id":"2308.10620","title":"Large Language Models for Software Engineering: A Systematic Literature Review","created":"2023-08-21","cited_by_count":399,"area":null},{"id":"2404.00971","title":"Beyond Functional Correctness: Exploring Hallucinations in LLM-Generated Code","created":"2024-04-01","cited_by_count":107,"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":"2403.09032","title":"CodeUltraFeedback: An LLM-as-a-Judge Dataset for Aligning Large Language Models to Coding Preferences","created":"2024-03-14","cited_by_count":57,"area":"alignment"},{"id":"2411.12924","title":"Human-In-the-Loop Software Development Agents","created":"2024-11-19","cited_by_count":42,"area":"agents"},{"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":"2405.02213","title":"Automatic Programming: Large Language Models and Beyond","created":"2024-05-03","cited_by_count":36,"area":null},{"id":"2503.01245","title":"Large Language Models for Code Generation: A Comprehensive Survey of Challenges, Techniques, Evaluation, and Applications","created":"2025-03-03","cited_by_count":26,"area":null},{"id":"2406.00215","title":"HumanEvalComm: Benchmarking the Communication Competence of Code Generation for LLMs and LLM Agent","created":"2024-05-31","cited_by_count":24,"area":"agents"},{"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":"2406.16441","title":"UniCoder: Scaling Code Large Language Model via Universal Code","created":"2024-06-24","cited_by_count":18,"area":null},{"id":"2410.12468","title":"Evaluating Software Development Agents: Patch Patterns, Code Quality, and Issue Complexity in Real-World GitHub Scenarios","created":"2024-10-16","cited_by_count":18,"area":"agents"},{"id":"2505.23387","title":"Afterburner: Reinforcement Learning Facilitates Self-Improving Code Efficiency Optimization","created":"2025-05-29","cited_by_count":18,"area":"alignment"},{"id":"2503.04779","title":"Can LLMs Reason About Program Semantics? A Comprehensive Evaluation of LLMs on Formal Specification Inference","created":"2025-02-22","cited_by_count":16,"area":"lr"},{"id":"2503.12374","title":"Beyond Final Code: A Process-Oriented Error Analysis of Software Development Agents in Real-World GitHub Scenarios","created":"2025-03-16","cited_by_count":14,"area":"agents"},{"id":"2504.20799","title":"Hallucination by Code Generation LLMs: Taxonomy, Benchmarks, Mitigation, and Challenges","created":"2025-04-29","cited_by_count":11,"area":null},{"id":"2504.00018","title":"SandboxEval: Towards Securing Test Environment for Untrusted Code","created":"2025-03-27","cited_by_count":10,"area":null},{"id":"2506.11022","title":"Security Degradation in Iterative AI Code Generation -- A Systematic Analysis of the Paradox","created":"2025-05-19","cited_by_count":10,"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":"2504.14640","title":"Risk Assessment Framework for Code LLMs via Leveraging Internal States","created":"2025-04-20","cited_by_count":9,"area":null},{"id":"2510.03029","title":"Investigating The Smells of LLM Generated Code","created":"2025-10-03","cited_by_count":9,"area":null},{"id":"2405.03616","title":"A Controlled Experiment on the Energy Efficiency of the Source Code Generated by Code Llama","created":"2024-05-06","cited_by_count":8,"area":null},{"id":"2411.08881","title":"Can We Trust AI Agents? A Case Study of an LLM-Based Multi-Agent System for Ethical AI","created":"2024-10-25","cited_by_count":6,"area":"agents"},{"id":"2501.04848","title":"Exploring Large Language Models for Semantic Analysis and Categorization of Android Malware","created":"2025-01-08","cited_by_count":6,"area":null},{"id":"2502.07487","title":"Multi-Agent Collaboration for Multilingual Code Instruction Tuning","created":"2025-02-11","cited_by_count":6,"area":"agents"},{"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":"2405.13101","title":"Evaluating AI-generated code for C++, Fortran, Go, Java, Julia, Matlab, Python, R, and Rust","created":"2024-05-21","cited_by_count":5,"area":null},{"id":"2411.09224","title":"Programming with AI: Evaluating ChatGPT, Gemini, AlphaCode, and GitHub Copilot for Programmers","created":"2024-11-14","cited_by_count":5,"area":null},{"id":"2412.16594","title":"AIGCodeSet: A New Annotated Dataset for AI Generated Code Detection","created":"2024-12-21","cited_by_count":5,"area":null},{"id":"2507.02976","title":"How Safe Are AI-Generated Patches? A Large-scale Study on Security Risks in LLM and Agentic Automated Program Repair on SWE-bench","created":"2025-06-30","cited_by_count":5,"area":"agents"},{"id":"2507.09866","title":"Turning the Tide: Repository-based Code Reflection","created":"2025-07-14","cited_by_count":5,"area":null},{"id":"2310.14211","title":"LUNA: A Model-Based Universal Analysis Framework for Large Language Models","created":"2023-10-22","cited_by_count":4,"area":null},{"id":"2501.11264","title":"Code Readability in the Age of Large Language Models: An Industrial Case Study from Atlassian","created":"2025-01-20","cited_by_count":4,"area":null},{"id":"2509.25242","title":"A Benchmark for Localizing Code and Non-Code Issues in Software Projects","created":"2025-09-26","cited_by_count":4,"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":"2510.22944","title":"Is Your Prompt Poisoning Code? Defect Induction Rates and Security Mitigation Strategies","created":"2025-10-27","cited_by_count":3,"area":null},{"id":"2601.20106","title":"Are We All Using Agents the Same Way? An Empirical Study of Core and Peripheral Developers Use of Coding Agents","created":"2026-01-27","cited_by_count":3,"area":"agents"},{"id":"2507.21693","title":"MultiAIGCD: A Comprehensive dataset for AI Generated Code Detection Covering Multiple Languages, Models,Prompts, and Scenarios","created":"2025-07-29","cited_by_count":2,"area":null},{"id":"2508.11257","title":"Hallucination in LLM-Based Code Generation: An Automotive Case Study","created":"2025-08-15","cited_by_count":2,"area":null},{"id":"2512.14792","title":"IaC Generation with LLMs: An Error Taxonomy and A Study on Configuration Knowledge Injection","created":"2025-12-16","cited_by_count":2,"area":"rag"},{"id":"2607.01867","title":"An Exploratory Study on LLM-Generated Code and Comments in Code Repositories","created":"2026-07-02","cited_by_count":2,"area":null},{"id":"2607.12962","title":"Form, Not Content? A Preregistered, Placebo-Controlled Evaluation of Learned Error-Conditioned Self-Repair Through Prompts and Weights in Frozen Small Code Models","created":"2026-07-14","cited_by_count":2,"area":null},{"id":"2406.04710","title":"Morescient GAI for Software Engineering (Extended Version)","created":"2024-06-07","cited_by_count":1,"area":null},{"id":"2406.10141","title":"The Rise and Fall(?) of Software Engineering","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2412.00707","title":"Protect Your Secrets: Understanding and Measuring Data Exposure in VSCode Extensions","created":"2024-12-01","cited_by_count":1,"area":null},{"id":"2501.19204","title":"Autonomous Legacy Web Application Upgrades Using a Multi-Agent System","created":"2025-01-31","cited_by_count":1,"area":"agents"},{"id":"2503.09020","title":"Enhancing the Non-Functional Quality Compliance of LLM-Generated Code through Quality-Aware Preference Learning","created":"2025-03-12","cited_by_count":1,"area":null},{"id":"2504.16485","title":"On Developers' Self-Declaration of AI-Generated Code: An Analysis of Practices","created":"2025-04-23","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":"2509.20277","title":"Investigating Security Implications of Automatically Generated Code on the Software Supply Chain","created":"2025-09-24","cited_by_count":1,"area":null},{"id":"2509.23835","title":"HFuzzer: Testing Large Language Models for Package Hallucinations via Phrase-based Fuzzing","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2512.22628","title":"M2G-Eval: Enhancing and Evaluating Multi-granularity Multilingual Code Generation","created":"2025-12-27","cited_by_count":1,"area":null},{"id":"2601.02060","title":"Perish or Flourish? A Holistic Evaluation of Large Language Models for Code Generation in Functional Programming","created":"2026-01-05","cited_by_count":1,"area":null},{"id":"2602.01187","title":"Autoregressive, Yet Revisable: In Decoding Revision for Secure Code Generation","created":"2026-02-01","cited_by_count":1,"area":null},{"id":"2605.05267","title":"Bridging Generation and Training: A Systematic Review of Quality Issues in LLMs for Code","created":"2026-05-06","cited_by_count":1,"area":null},{"id":"2606.09800","title":"FASE: Fast Adaptive Semantic Entropy for Code Quality","created":"2026-06-08","cited_by_count":1,"area":null},{"id":"2608.11965","title":"Developing LLM-based Multi-Agent Systems in Software Engineering: A Mixed-Method Experience Report","created":"2026-08-12","cited_by_count":1,"area":"agents"},{"id":"2403.10507","title":"Demystifying Faulty Code with LLM: Step-by-Step Reasoning for Explainable Fault Localization","created":"2024-03-15","cited_by_count":0,"area":"lr"},{"id":"2502.18467","title":"ChatGPT vs. DeepSeek: A Comparative Study on AI-Based Code Generation","created":"2025-01-30","cited_by_count":0,"area":null},{"id":"2508.04125","title":"Experimental Analysis of Productive Interaction Strategy with ChatGPT: User Study on Function and Project-level Code Generation Tasks","created":"2025-08-06","cited_by_count":0,"area":null},{"id":"2508.11665","title":"StackPilot: Autonomous Function Agents for Scalable and Environment-Free Code Execution","created":"2025-08-06","cited_by_count":0,"area":"agents"},{"id":"2510.04397","title":"MulVuln: Enhancing Pre-trained LMs with Shared and Language-Specific Knowledge for Multilingual Vulnerability Detection","created":"2025-10-05","cited_by_count":0,"area":null},{"id":"2510.13992","title":"Signature in Code Backdoor Detection, how far are we?","created":"2025-10-15","cited_by_count":0,"area":"safety"},{"id":"2512.08057","title":"Large Language Models for Education and Research: An Empirical and User Survey-based Analysis","created":"2025-12-08","cited_by_count":0,"area":null},{"id":"2601.22461","title":"Toward Non-Expert Customized Congestion Control: Large Language Model-Assisted CCA Code Generation with eBPF Deployment","created":"2026-01-30","cited_by_count":0,"area":null},{"id":"2604.07755","title":"An Empirical Analysis of Static Analysis Methods for Detection and Mitigation of Code Library Hallucinations","created":"2026-04-09","cited_by_count":0,"area":null},{"id":"2605.06136","title":"BUILD-AND-FIND: An Effort-Aware Protocol for Evaluating Agent-Managed Codebases","created":"2026-05-07","cited_by_count":0,"area":null},{"id":"2605.17029","title":"Task Abstention for Large Language Models in Code Generation","created":"2026-05-16","cited_by_count":0,"area":null},{"id":"2605.29493","title":"The New Pro Se: Generative AI and the Surge in Federal Civil Self-Representation","created":"2026-05-28","cited_by_count":0,"area":null},{"id":"2606.21171","title":"An Exploratory Case Study of LLM-Assisted Refactoring and Gameplay Feature Generation in an Endless Runner Game","created":"2026-06-19","cited_by_count":0,"area":null},{"id":"2606.24834","title":"Accuracy and Satisfaction in Multi-Turn LLM Dialogues for NFR Assessment","created":"2026-06-23","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":"2608.06640","title":"Characterizing the Quality Profile of AI-Generated C++ in Production","created":"2026-08-06","cited_by_count":0,"area":null},{"id":"2608.16318","title":"Revisiting the Performance of Generative Artificial Intelligence on Introductory Object-Oriented Programming Assessments: Insights from 2026","created":"2026-08-17","cited_by_count":0,"area":null},{"id":"2609.12708","title":"What is the Difference Between Me and You? Benchmarking the Quality Gap Between Human-Written and AI-Generated Code","created":"2026-09-11","cited_by_count":0,"area":null},{"id":"2610.00425","title":"Code That Works, Environments That Don't: Measuring Environment Reproducibility in AI-Generated Software","created":"2026-09-30","cited_by_count":0,"area":"agents"}],"next_cursor":null}