{"total":166,"rows":[{"id":"2310.06770","title":"SWE-bench: Can Language Models Resolve Real-World GitHub Issues?","created":"2023-10-10","cited_by_count":3373,"area":null},{"id":"2404.13501","title":"A Survey on the Memory Mechanism of Large Language Model based Agents","created":"2024-04-21","cited_by_count":634,"area":"wm"},{"id":"2406.15877","title":"BigCodeBench: Benchmarking Code Generation with Diverse Function Calls and Complex Instructions","created":"2024-06-22","cited_by_count":546,"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":"2409.02977","title":"Large Language Model-Based Agents for Software Engineering: A Survey","created":"2024-09-04","cited_by_count":178,"area":"agents"},{"id":"2311.07989","title":"Unifying the Perspectives of NLP and Software Engineering: A Survey on Language Models for Code","created":"2023-11-14","cited_by_count":62,"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":"2405.19479","title":"Participation in the age of foundation models","created":"2024-05-29","cited_by_count":32,"area":null},{"id":"2401.13810","title":"Automated Root Causing of Cloud Incidents using In-Context Learning with GPT-4","created":"2024-01-24","cited_by_count":28,"area":null},{"id":"2401.16186","title":"An Empirical Study on Usage and Perceptions of LLMs in a Software Engineering Project","created":"2024-01-29","cited_by_count":28,"area":null},{"id":"2403.11671","title":"HDLdebugger: Streamlining HDL debugging with Large Language Models","created":"2024-03-18","cited_by_count":26,"area":null},{"id":"2404.08817","title":"Revisiting Code Similarity Evaluation with Abstract Syntax Tree Edit Distance","created":"2024-04-12","cited_by_count":26,"area":null},{"id":"2501.12862","title":"Mutation-Guided LLM-based Test Generation at Meta","created":"2025-01-22","cited_by_count":25,"area":null},{"id":"2404.18353","title":"How secure is AI-generated Code: A Large-Scale Comparison of Large Language Models","created":"2024-04-29","cited_by_count":24,"area":null},{"id":"2406.07737","title":"The Future of AI-Driven Software Engineering","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2402.01386","title":"Can Large Language Models Serve as Data Analysts? A Multi-Agent Assisted Approach for Qualitative Data Analysis","created":"2024-02-02","cited_by_count":20,"area":"agents"},{"id":"2401.03038","title":"SPADE: Synthesizing Data Quality Assertions for Large Language Model Pipelines","created":"2024-01-05","cited_by_count":19,"area":"synth"},{"id":"2404.03662","title":"X-lifecycle Learning for Cloud Incident Management using LLMs","created":"2024-02-15","cited_by_count":19,"area":null},{"id":"2402.01874","title":"The RL/LLM Taxonomy Tree: Reviewing Synergies Between Reinforcement Learning and Large Language Models","created":"2024-02-02","cited_by_count":15,"area":null},{"id":"2503.13310","title":"Generative AI for Software Architecture. Applications, Challenges, and Future Directions","created":"2025-03-17","cited_by_count":15,"area":null},{"id":"2504.07137","title":"Large Language Model (LLM) for Software Security: Code Analysis, Malware Analysis, Reverse Engineering","created":"2025-04-07","cited_by_count":15,"area":null},{"id":"2310.06266","title":"CodeFuse-13B: A Pretrained Multi-lingual Code Large Language Model","created":"2023-10-10","cited_by_count":14,"area":null},{"id":"2412.20545","title":"The Impact of Prompt Programming on Function-Level Code Generation","created":"2024-12-29","cited_by_count":13,"area":null},{"id":"2510.25506","title":"Reflections on the Reproducibility of Commercial LLM Performance in Empirical Software Engineering Studies","created":"2025-10-29","cited_by_count":12,"area":null},{"id":"2511.02108","title":"Metamorphic Testing of Large Language Models for Natural Language Processing","created":"2025-11-03","cited_by_count":12,"area":null},{"id":"2402.11702","title":"Can ChatGPT Support Developers? An Empirical Evaluation of Large Language Models for Code Generation","created":"2024-02-18","cited_by_count":11,"area":null},{"id":"2408.11710","title":"Leveraging Large Language Models for Enhancing the Understandability of Generated Unit Tests","created":"2024-08-21","cited_by_count":11,"area":null},{"id":"2411.00585","title":"Fairness Testing of Large Language Models in Role-Playing","created":"2024-11-01","cited_by_count":11,"area":null},{"id":"2411.00932","title":"LLMs: A Game-Changer for Software Engineers?","created":"2024-11-01","cited_by_count":11,"area":null},{"id":"2502.18474","title":"A Contemporary Survey of Large Language Model Assisted Program Analysis","created":"2025-02-05","cited_by_count":11,"area":null},{"id":"2404.01023","title":"Large Language Model Evaluation Via Multi AI Agents: Preliminary results","created":"2024-04-01","cited_by_count":10,"area":"agents"},{"id":"2408.03519","title":"RepoMasterEval: Evaluating Code Completion via Real-World Repositories","created":"2024-08-07","cited_by_count":10,"area":null},{"id":"2409.15186","title":"Location is Key: Leveraging Large Language Model for Functional Bug Localization in Verilog","created":"2024-09-23","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":"2403.15230","title":"An Exploratory Investigation into Code License Infringements in Large Language Model Training Datasets","created":"2024-03-22","cited_by_count":9,"area":null},{"id":"2409.10756","title":"VulnLLMEval: A Framework for Evaluating Large Language Models in Software Vulnerability Detection and Patching","created":"2024-09-16","cited_by_count":9,"area":null},{"id":"2502.04008","title":"Automating a Complete Software Test Process Using LLMs: An Automotive Case Study","created":"2025-02-06","cited_by_count":8,"area":null},{"id":"2502.08806","title":"CLOVER: A Test Case Generation Benchmark with Coverage, Long-Context, and Verification","created":"2025-02-12","cited_by_count":8,"area":null},{"id":"2505.10593","title":"LLM-Explorer: Towards Efficient and Affordable LLM-based Exploration for Mobile Apps","created":"2025-05-15","cited_by_count":8,"area":null},{"id":"2510.09907","title":"Agentic Property-Based Testing: Finding Bugs Across the Python Ecosystem","created":"2025-10-10","cited_by_count":8,"area":"agents"},{"id":"2310.07856","title":"Assessing Evaluation Metrics for Neural Test Oracle Generation","created":"2023-10-11","cited_by_count":7,"area":null},{"id":"2605.12913","title":"Revisiting DAgger in the Era of LLM-Agents","created":"2026-05-13","cited_by_count":7,"area":"agents"},{"id":"2404.08517","title":"Online Safety Analysis for LLMs: a Benchmark, an Assessment, and a Path Forward","created":"2024-04-12","cited_by_count":6,"area":null},{"id":"2406.05381","title":"Experimenting with Multi-Agent Software Development: Towards a Unified Platform","created":"2024-06-08","cited_by_count":6,"area":"agents"},{"id":"2410.09012","title":"Software Engineering and Foundation Models: Insights from Industry Blogs Using a Jury of Foundation Models","created":"2024-10-11","cited_by_count":6,"area":null},{"id":"2411.01789","title":"Generating executable oracles to check conformance of client code to requirements of JDK Javadocs using LLMs","created":"2024-11-04","cited_by_count":6,"area":null},{"id":"2411.09261","title":"Automating Autograding: Large Language Models as Test Suite Generators for Introductory Programming","created":"2024-11-14","cited_by_count":6,"area":null},{"id":"2504.01495","title":"Are Autonomous Web Agents Good Testers?","created":"2025-04-02","cited_by_count":6,"area":"agents"},{"id":"2311.07377","title":"Testing learning-enabled cyber-physical systems with Large-Language Models: A Formal Approach","created":"2023-11-13","cited_by_count":5,"area":null},{"id":"2402.09615","title":"API Pack: A Massive Multi-Programming Language Dataset for API Call Generation","created":"2024-02-14","cited_by_count":5,"area":null},{"id":"2408.11198","title":"Automated Prompt Engineering for Cost-Effective Code Generation Using Evolutionary Algorithm","created":"2024-08-20","cited_by_count":5,"area":null},{"id":"2408.13372","title":"Understanding Defects in Generated Codes by Language Models","created":"2024-08-23","cited_by_count":5,"area":null},{"id":"2411.02318","title":"Evaluating the Ability of Large Language Models to Generate Verifiable Specifications in VeriFast","created":"2024-11-04","cited_by_count":5,"area":null},{"id":"2503.12205","title":"PredicateFix: Repairing Static Analysis Alerts with Bridging Predicates","created":"2025-03-15","cited_by_count":5,"area":"rag"},{"id":"2503.15079","title":"LogiAgent: Automated Logical Testing for REST Systems with LLM-Based Multi-Agents","created":"2025-03-19","cited_by_count":5,"area":"agents"},{"id":"2511.04064","title":"Benchmarking and Studying the LLM-based Agent System in End-to-End Software Development","created":"2025-11-06","cited_by_count":5,"area":"agents"},{"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":"2401.08138","title":"LLMs for Test Input Generation for Semantic Caches","created":"2024-01-16","cited_by_count":4,"area":null},{"id":"2402.00350","title":"On the Challenges of Fuzzing Techniques via Large Language Models","created":"2024-02-01","cited_by_count":4,"area":null},{"id":"2404.06201","title":"Open-Source AI-based SE Tools: Opportunities and Challenges of Collaborative Software Learning","created":"2024-04-09","cited_by_count":4,"area":null},{"id":"2405.14619","title":"exLong: Generating Exceptional Behavior Tests with Large Language Models","created":"2024-05-23","cited_by_count":4,"area":null},{"id":"2411.08254","title":"Toward Automated Validation of Language Model Synthesized Test Cases using Semantic Entropy","created":"2024-11-13","cited_by_count":4,"area":null},{"id":"2411.15442","title":"Automatic High-quality Verilog Assertion Generation through Subtask-Focused Fine-Tuned LLMs and Iterative Prompting","created":"2024-11-23","cited_by_count":4,"area":null},{"id":"2501.08598","title":"LlamaRestTest: Effective REST API Testing with Small Language Models","created":"2025-01-15","cited_by_count":4,"area":null},{"id":"2501.11031","title":"AdaptiveLog: An Adaptive Log Analysis Framework with the Collaboration of Large and Small Language Model","created":"2025-01-19","cited_by_count":4,"area":null},{"id":"2502.16071","title":"Improving Deep Assertion Generation via Fine-Tuning Retrieval-Augmented Pre-trained Language Models","created":"2025-02-22","cited_by_count":4,"area":"rag"},{"id":"2507.03156","title":"The Impact of LLM-Assistants on Software Developer Productivity: A Systematic Review and Mapping Study","created":"2025-07-03","cited_by_count":4,"area":null},{"id":"2509.16950","title":"Temporal Logic-Based Multi-Vehicle Backdoor Attacks against Offline RL Agents in End-to-end Autonomous Driving","created":"2025-09-21","cited_by_count":4,"area":"safety"},{"id":"2606.31511","title":"Falsification, Not Exposure: An Internally Preregistered Placebo-Controlled Decomposition of Self-Repair Feedback in Frozen Small Code Models","created":"2026-06-30","cited_by_count":4,"area":null},{"id":"2312.00024","title":"Can LLMs Patch Security Issues?","created":"2023-11-13","cited_by_count":3,"area":null},{"id":"2410.03062","title":"Image First or Text First? Optimising the Sequencing of Modalities in Large Language Model Prompting and Reasoning Tasks","created":"2024-10-04","cited_by_count":3,"area":"lr"},{"id":"2503.07556","title":"Novice Developers' Perspectives on Adopting LLMs for Software Development: A Systematic Literature Review","created":"2025-03-10","cited_by_count":3,"area":null},{"id":"2506.16586","title":"AI-Driven Tools in Modern Software Quality Assurance: An Assessment of Benefits, Challenges, and Future Directions","created":"2025-06-19","cited_by_count":3,"area":null},{"id":"2509.05540","title":"Combining TSL and LLM to Automate REST API Testing: A Comparative Study","created":"2025-09-05","cited_by_count":3,"area":null},{"id":"2604.16321","title":"LLM-Based Multi-Agent Systems for Code Generation: A Multi-Vocal Literature Review","created":"2026-02-25","cited_by_count":3,"area":"agents"},{"id":"2604.16335","title":"Beyond Verifiable Rewards: Rubric-Based GRM for Reinforced Fine-Tuning SWE Agents","created":"2026-03-13","cited_by_count":3,"area":"agents"},{"id":"2404.03664","title":"LLMs in the Heart of Differential Testing: A Case Study on a Medical Rule Engine","created":"2024-02-16","cited_by_count":2,"area":null},{"id":"2404.09384","title":"Generative transformations and patterns in LLM-native approaches for software verification and falsification","created":"2024-04-14","cited_by_count":2,"area":null},{"id":"2405.03509","title":"Are Human Rules Necessary? Generating Reusable APIs with CoT Reasoning and In-Context Learning","created":"2024-05-06","cited_by_count":2,"area":"lr"},{"id":"2409.01909","title":"LUK: Empowering Log Understanding with Expert Knowledge from Large Language Models","created":"2024-09-03","cited_by_count":2,"area":null},{"id":"2409.06416","title":"Exploring the Integration of Large Language Models in Industrial Test Maintenance Processes","created":"2024-09-10","cited_by_count":2,"area":null},{"id":"2409.10574","title":"Detection Made Easy: Potentials of Large Language Models for Solidity Vulnerabilities","created":"2024-09-15","cited_by_count":2,"area":null},{"id":"2412.06684","title":"Exploring Critical Testing Scenarios for Decision-Making Policies: An LLM Approach","created":"2024-12-09","cited_by_count":2,"area":null},{"id":"2502.02715","title":"An Analysis of LLM Fine-Tuning and Few-Shot Learning for Flaky Test Detection and Classification","created":"2025-02-04","cited_by_count":2,"area":null},{"id":"2502.10696","title":"Improving Retrieval-Augmented Deep Assertion Generation via Joint Training","created":"2025-02-15","cited_by_count":2,"area":"rag"},{"id":"2505.22818","title":"A Tool for Generating Exceptional Behavior Tests With Large Language Models","created":"2025-05-28","cited_by_count":2,"area":null},{"id":"2507.04469","title":"The role of large language models in UI/UX design: A systematic literature review","created":"2025-07-06","cited_by_count":2,"area":null},{"id":"2509.20190","title":"STAF: Leveraging LLMs for Automated Attack Tree-Based Security Test Generation","created":"2025-09-24","cited_by_count":2,"area":null},{"id":"2509.24975","title":"DiffuTester: Accelerating Unit Test Generation for Diffusion LLMs via Mining Structural Pattern","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2509.25043","title":"Large Language Models for Software Testing: A Research Roadmap","created":"2025-09-29","cited_by_count":2,"area":null},{"id":"2511.06428","title":"Walking the Tightrope of LLMs for Software Development: A Practitioners' Perspective","created":"2025-11-09","cited_by_count":2,"area":null},{"id":"2601.05542","title":"Understanding LLM-Driven Test Oracle Generation","created":"2026-01-09","cited_by_count":2,"area":null},{"id":"2607.02186","title":"UA-ChatDev: Uncertainty-Aware Multi-Agent Collaboration for Reliable Software Development","created":"2026-07-02","cited_by_count":2,"area":"agents"},{"id":"2406.04710","title":"Morescient GAI for Software Engineering (Extended Version)","created":"2024-06-07","cited_by_count":1,"area":null},{"id":"2406.10305","title":"Unlock the Correlation between Supervised Fine-Tuning and Reinforcement Learning in Training Code Large Language Models","created":"2024-06-14","cited_by_count":1,"area":null},{"id":"2406.16739","title":"Agent-Driven Automatic Software Improvement","created":"2024-06-24","cited_by_count":1,"area":"agents"},{"id":"2409.12405","title":"On the Effectiveness of LLMs for Manual Test Verifications","created":"2024-09-19","cited_by_count":1,"area":null},{"id":"2410.20975","title":"Geo-FuB: A Method for Constructing an Operator-Function Knowledge Base for Geospatial Code Generation Tasks Using Large Language Models","created":"2024-10-28","cited_by_count":1,"area":null},{"id":"2412.01526","title":"Addressing Data Leakage in HumanEval Using Combinatorial Test Design","created":"2024-12-02","cited_by_count":1,"area":null},{"id":"2503.03951","title":"WIP: Assessing the Effectiveness of ChatGPT in Preparatory Testing Activities","created":"2025-03-05","cited_by_count":1,"area":null}],"next_cursor":"100"}