{"total":194,"rows":[{"id":"2403.07974","title":"LiveCodeBench: Holistic and Contamination Free Evaluation of Large Language Models for Code","created":"2024-03-12","cited_by_count":2004,"area":"lr"},{"id":"2502.18449","title":"SWE-RL: Advancing LLM Reasoning via Reinforcement Learning on Open Software Evolution","created":"2025-02-25","cited_by_count":263,"area":"lr"},{"id":"2312.02120","title":"Magicoder: Empowering Code Generation with OSS-Instruct","created":"2023-12-04","cited_by_count":256,"area":null},{"id":"2403.17134","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","created":"2024-03-25","cited_by_count":232,"area":"agents"},{"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":"2406.12952","title":"SWT-Bench: Testing and Validating Real-World Bug-Fixes with Code Agents","created":"2024-06-18","cited_by_count":133,"area":"agents"},{"id":"2304.00385","title":"Keep the Conversation Going: Fixing 162 out of 337 bugs for $0.42 each using ChatGPT","created":"2023-04-01","cited_by_count":125,"area":null},{"id":"2402.00097","title":"Code-Aware Prompting: A study of Coverage Guided Test Generation in Regression Setting using LLM","created":"2024-01-31","cited_by_count":64,"area":null},{"id":"2504.04030","title":"OpenCodeInstruct: A Large-scale Instruction Tuning Dataset for Code LLMs","created":"2025-04-05","cited_by_count":60,"area":null},{"id":"2506.03136","title":"Co-Evolving LLM Coder and Unit Tester via Reinforcement Learning","created":"2025-06-03","cited_by_count":56,"area":null},{"id":"2412.10133","title":"You Name It, I Run It: An LLM Agent to Execute Tests of Arbitrary Projects","created":"2024-12-13","cited_by_count":47,"area":"agents"},{"id":"2410.01215","title":"From Code to Correctness: Closing the Last Mile of Code Generation with Hierarchical Debugging","created":"2024-10-02","cited_by_count":46,"area":null},{"id":"2408.05534","title":"Can LLMs Replace Manual Annotation of Software Engineering Artifacts?","created":"2024-08-10","cited_by_count":42,"area":null},{"id":"2411.12924","title":"Human-In-the-Loop Software Development Agents","created":"2024-11-19","cited_by_count":42,"area":"agents"},{"id":"2501.09655","title":"A Survey of Research in Large Language Models for Electronic Design Automation","created":"2025-01-16","cited_by_count":41,"area":null},{"id":"2401.12224","title":"LLM4EDA: Emerging Progress in Large Language Models for Electronic Design Automation","created":"2023-12-28","cited_by_count":40,"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":"2402.13521","title":"Test-Driven Development for Code Generation","created":"2024-02-21","cited_by_count":34,"area":null},{"id":"2402.13610","title":"Data-driven Discovery with Large Generative Models","created":"2024-02-21","cited_by_count":34,"area":null},{"id":"2403.15852","title":"SOEN-101: Code Generation by Emulating Software Process Models Using Large Language Model Agents","created":"2024-03-23","cited_by_count":34,"area":"agents"},{"id":"2302.10166","title":"Learning Deep Semantics for Test Completion","created":"2023-02-20","cited_by_count":31,"area":null},{"id":"2404.13340","title":"Large Language Models as Test Case Generators: Performance Evaluation and Enhancement","created":"2024-04-20","cited_by_count":28,"area":null},{"id":"2405.11430","title":"MHPP: Exploring the Capabilities and Limitations of Language Models Beyond Basic Code Generation","created":"2024-05-19","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":"2502.05368","title":"Otter: Generating Tests from Issues to Validate SWE Patches","created":"2025-02-07","cited_by_count":25,"area":null},{"id":"2310.04535","title":"LLM4DV: Using Large Language Models for Hardware Test Stimuli Generation","created":"2023-10-06","cited_by_count":23,"area":null},{"id":"2406.07737","title":"The Future of AI-Driven Software Engineering","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2402.02018","title":"The Landscape and Challenges of HPC Research and LLMs","created":"2024-02-03","cited_by_count":22,"area":null},{"id":"2502.01821","title":"Agentic Bug Reproduction for Effective Automated Program Repair at Google","created":"2025-02-03","cited_by_count":22,"area":"agents"},{"id":"2310.02368","title":"Reinforcement Learning from Automatic Feedback for High-Quality Unit Test Generation","created":"2023-10-03","cited_by_count":21,"area":"alignment"},{"id":"2404.18864","title":"Performance-Aligned LLMs for Generating Fast Code","created":"2024-04-29","cited_by_count":21,"area":null},{"id":"2405.20092","title":"Divide-and-Conquer Meets Consensus: Unleashing the Power of Functions in Code Generation","created":"2024-05-30","cited_by_count":19,"area":null},{"id":"2602.02361","title":"SWE-Universe: Scale Real-World Verifiable Environments to Millions","created":"2026-02-02","cited_by_count":19,"area":null},{"id":"2501.12934","title":"Correctness Assessment of Code Generated by Large Language Models Using Internal Representations","created":"2025-01-22","cited_by_count":17,"area":null},{"id":"2502.01619","title":"Learning to Generate Unit Tests for Automated Debugging","created":"2025-02-03","cited_by_count":17,"area":null},{"id":"2310.04963","title":"LLM4VV: Developing LLM-Driven Testsuite for Compiler Validation","created":"2023-10-08","cited_by_count":15,"area":null},{"id":"2407.00456","title":"Beyond Functional Correctness: Investigating Coding Style Inconsistencies in Large Language Models","created":"2024-06-29","cited_by_count":15,"area":null},{"id":"2511.18538","title":"From Code Foundation Models to Agents and Applications: A Comprehensive Survey and Practical Guide to Code Intelligence","created":"2025-11-23","cited_by_count":15,"area":"agents"},{"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":"2404.10304","title":"LLM-Powered Test Case Generation for Detecting Bugs in Plausible Programs","created":"2024-04-16","cited_by_count":14,"area":null},{"id":"2502.10802","title":"CoCoEvo: Co-Evolution of Programs and Test Cases to Enhance Code Generation","created":"2025-02-15","cited_by_count":14,"area":null},{"id":"2504.09691","title":"Migrating Code At Scale With LLMs At Google","created":"2025-04-13","cited_by_count":14,"area":null},{"id":"2312.10622","title":"Unit Test Generation using Generative AI : A Comparative Performance Analysis of Autogeneration Tools","created":"2023-12-17","cited_by_count":13,"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":"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":"2409.09464","title":"Measuring the Influence of Incorrect Code on Test Generation","created":"2024-09-14","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":"2502.18917","title":"ClassInvGen: Class Invariant Synthesis using Large Language Models","created":"2025-02-26","cited_by_count":11,"area":null},{"id":"2605.26563","title":"TrajAudit: Automated Failure Diagnosis for Agentic Coding Systems","created":"2026-05-26","cited_by_count":11,"area":"agents"},{"id":"2406.12902","title":"JavaBench: A Benchmark of Object-Oriented Code Generation for Evaluating Large Language Models","created":"2024-06-10","cited_by_count":10,"area":null},{"id":"2408.03519","title":"RepoMasterEval: Evaluating Code Completion via Real-World Repositories","created":"2024-08-07","cited_by_count":10,"area":null},{"id":"2409.08692","title":"B4: Towards Optimal Assessment of Plausible Code Solutions with Plausible Tests","created":"2024-09-13","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":"2503.05070","title":"PromptPex: Automatic Test Generation for Language Model Prompts","created":"2025-03-07","cited_by_count":9,"area":null},{"id":"2503.13580","title":"LLM Test Generation via Iterative Hybrid Program Analysis","created":"2025-03-17","cited_by_count":9,"area":null},{"id":"2503.14713","title":"TestForge: Feedback-Driven, Agentic Test Suite Generation","created":"2025-03-18","cited_by_count":9,"area":"agents"},{"id":"2506.02943","title":"Hallucination to Consensus: Multi-Agent LLMs for End-to-End JUnit Test Generation","created":"2025-06-03","cited_by_count":9,"area":"agents"},{"id":"2509.10858","title":"Large Language Models for Security Operations Centers: A Comprehensive Survey","created":"2025-09-13","cited_by_count":9,"area":null},{"id":"2408.07846","title":"A System for Automated Unit Test Generation Using Large Language Models and Assessment of Generated Test Suites","created":"2024-08-14","cited_by_count":8,"area":null},{"id":"2508.00408","title":"Benchmarking LLMs for Unit Test Generation from Real-World Functions","created":"2025-08-01","cited_by_count":8,"area":null},{"id":"2601.09822","title":"LLM-Based Agentic Systems for Software Engineering: Challenges and Opportunities","created":"2026-01-14","cited_by_count":8,"area":"agents"},{"id":"2603.23613","title":"LLMLOOP: Improving LLM-Generated Code and Tests through Automated Iterative Feedback Loops","created":"2026-03-24","cited_by_count":8,"area":null},{"id":"2308.08033","title":"Domain Adaptation for Code Model-based Unit Test Case Generation","created":"2023-08-15","cited_by_count":7,"area":null},{"id":"2407.03611","title":"An Empirical Study on Capability of Large Language Models in Understanding Code Semantics","created":"2024-07-04","cited_by_count":7,"area":null},{"id":"2409.12682","title":"Retrieval-Augmented Test Generation: How Far Are We?","created":"2024-09-19","cited_by_count":7,"area":"rag"},{"id":"2501.16961","title":"Instantiation-based Formalization of Logical Reasoning Tasks using Language Models and Logical Solvers","created":"2025-01-28","cited_by_count":7,"area":"lr"},{"id":"2602.08146","title":"Test vs Mutant: Adversarial LLM Agents for Robust Unit Test Generation","created":"2026-02-08","cited_by_count":7,"area":"agents"},{"id":"2310.16673","title":"Exploring Large Language Models for Code Explanation","created":"2023-10-25","cited_by_count":6,"area":null},{"id":"2401.16310","title":"An Insight into Security Code Review with LLMs: Capabilities, Obstacles, and Influential Factors","created":"2024-01-29","cited_by_count":6,"area":"lr"},{"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":"2412.02906","title":"Does Few-Shot Learning Help LLM Performance in Code Synthesis?","created":"2024-12-03","cited_by_count":6,"area":"lr"},{"id":"2501.11086","title":"Evaluating LLM-Based Regression Test Generation","created":"2025-01-19","cited_by_count":6,"area":null},{"id":"2502.14930","title":"RAGVA: Engineering Retrieval Augmented Generation-based Virtual Assistants in Practice","created":"2025-02-20","cited_by_count":6,"area":"rag"},{"id":"2602.00409","title":"Are Coding Agents Generating Over-Mocked Tests? An Empirical Study","created":"2026-01-30","cited_by_count":6,"area":"agents"},{"id":"2402.03130","title":"User Centric Evaluation of Code Generation Tools","created":"2024-02-05","cited_by_count":5,"area":null},{"id":"2402.03396","title":"UniTSyn: A Large-Scale Dataset Capable of Enhancing the Prowess of Large Language Models for Program Testing","created":"2024-02-04","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":"2312.04687","title":"LLM4TDD: Best Practices for Test Driven Development Using Large Language Models","created":"2023-12-07","cited_by_count":4,"area":null},{"id":"2401.17626","title":"Generative AI to Generate Test Data Generators","created":"2024-01-31","cited_by_count":4,"area":null},{"id":"2404.03114","title":"Testing the Effect of Code Documentation on Large Language Model Code Understanding","created":"2024-04-03","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":"2408.15630","title":"CodeSift: An LLM-Based Reference-Less Framework for Automatic Code Validation","created":"2024-08-28","cited_by_count":4,"area":null},{"id":"2411.16927","title":"ASSERTIFY: Utilizing Large Language Models to Generate Assertions for Production Code","created":"2024-11-25","cited_by_count":4,"area":null},{"id":"2412.13464","title":"GenX: Mastering Code and Test Generation with Execution Feedback","created":"2024-12-18","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":"2502.06556","title":"MultiFileTest: A Multi-File-Level LLM Unit Test Generation Benchmark and Impact of Error Fixing Mechanisms","created":"2025-02-10","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":"2510.07740","title":"AppForge: From Assistant to Independent Developer -- Are GPTs Ready for Software Development?","created":"2025-10-09","cited_by_count":4,"area":null},{"id":"2510.26423","title":"Nexus: Execution-Grounded Multi-Agent Test Oracle Synthesis","created":"2025-10-30","cited_by_count":4,"area":"agents"},{"id":"2406.08665","title":"FuzzAug: Data Augmentation by Coverage-guided Fuzzing for Neural Test Generation","created":"2024-06-12","cited_by_count":3,"area":null},{"id":"2407.05202","title":"Harnessing the Power of LLMs: Automating Unit Test Generation for High-Performance Computing","created":"2024-07-06","cited_by_count":3,"area":null},{"id":"2411.02462","title":"Parameter-Efficient Fine-Tuning of Large Language Models for Unit Test Generation: An Empirical Study","created":"2024-11-04","cited_by_count":3,"area":null},{"id":"2501.07892","title":"Leveraging Metamemory Agent for Enhanced Data-Free Code Generation in Large Language Models","created":"2025-01-14","cited_by_count":3,"area":"agents"},{"id":"2502.11167","title":"SURGE: On the Potential of Large Language Models as General-Purpose Surrogate Code Executors","created":"2025-02-16","cited_by_count":3,"area":null},{"id":"2505.17928","title":"Towards Practical Defect-Focused Automated Code Review","created":"2025-05-23","cited_by_count":3,"area":null},{"id":"2510.00591","title":"AI-Driven Self-Evolving Software: A Promising Path Toward Software Automation","created":"2025-10-01","cited_by_count":3,"area":null},{"id":"2601.09703","title":"ShortCoder: Knowledge-Augmented Syntax Optimization for Token-Efficient Code Generation","created":"2026-01-14","cited_by_count":3,"area":"inference"},{"id":"2605.15301","title":"Solvita: Enhancing Large Language Models for Competitive Programming via Agentic Evolution","created":"2026-05-14","cited_by_count":3,"area":"agents"},{"id":"2607.15684","title":"Understanding Agent-Reactive Bugs at the Model-Harness Boundary: An Empirical Study of LLM Agent Issue Reports","created":"2026-07-17","cited_by_count":3,"area":"agents"},{"id":"2311.16267","title":"Novel Preprocessing Technique for Data Embedding in Engineering Code Generation Using Large Language Model","created":"2023-11-27","cited_by_count":2,"area":null}],"next_cursor":"100"}