{"total":118,"rows":[{"id":"2107.03374","title":"Evaluating Large Language Models Trained on Code","created":"2021-07-07","cited_by_count":8320,"area":null},{"id":"2308.12950","title":"Code Llama: Open Foundation Models for Code","created":"2023-08-24","cited_by_count":2139,"area":"lr"},{"id":"2102.04664","title":"CodeXGLUE: A Machine Learning Benchmark Dataset for Code Understanding and Generation","created":"2021-02-09","cited_by_count":744,"area":null},{"id":"2211.11501","title":"DS-1000: A Natural and Reliable Benchmark for Data Science Code Generation","created":"2022-11-18","cited_by_count":452,"area":null},{"id":"2207.10397","title":"CodeT: Code Generation with Generated Tests","created":"2022-07-21","cited_by_count":384,"area":null},{"id":"2302.08468","title":"LEVER: Learning to Verify Language-to-Code Generation with Execution","created":"2023-02-16","cited_by_count":239,"area":"lr"},{"id":"2302.06527","title":"An Empirical Evaluation of Using Large Language Models for Automated Unit Test Generation","created":"2023-02-13","cited_by_count":194,"area":null},{"id":"2303.05510","title":"Planning with Large Language Models for Code Generation","created":"2023-03-09","cited_by_count":182,"area":null},{"id":"2301.03988","title":"SantaCoder: don't reach for the stars!","created":"2023-01-09","cited_by_count":170,"area":null},{"id":"2208.08227","title":"MultiPL-E: A Scalable and Extensible Approach to Benchmarking Neural Code Generation","created":"2022-08-17","cited_by_count":136,"area":null},{"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":"2302.07867","title":"Learning Performance-Improving Code Edits","created":"2023-02-15","cited_by_count":106,"area":null},{"id":"2212.10481","title":"Execution-Based Evaluation for Open-Domain Code Generation","created":"2022-12-20","cited_by_count":91,"area":null},{"id":"2408.02479","title":"From LLMs to LLM-based Agents for Software Engineering: A Survey of Current, Challenges and Future","created":"2024-08-05","cited_by_count":86,"area":"agents"},{"id":"2110.06773","title":"Leveraging Automated Unit Tests for Unsupervised Code Translation","created":"2021-10-13","cited_by_count":82,"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":"2310.01831","title":"Can Large Language Models Transform Natural Language Intent into Formal Method Postconditions?","created":"2023-10-03","cited_by_count":57,"area":null},{"id":"2404.14646","title":"Exploring and Unleashing the Power of Large Language Models in Automated Code Translation","created":"2024-04-23","cited_by_count":57,"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":"2305.00418","title":"Using Large Language Models to Generate JUnit Tests: An Empirical Study","created":"2023-04-30","cited_by_count":53,"area":null},{"id":"2411.17501","title":"The Limits of Inference Scaling Through Resampling","created":"2024-11-26","cited_by_count":53,"area":null},{"id":"2208.05950","title":"Interactive Code Generation via Test-Driven User-Intent Formalization","created":"2022-08-11","cited_by_count":50,"area":null},{"id":"2202.04903","title":"Investigating Explainability of Generative AI for Code through Scenario-based Design","created":"2022-02-10","cited_by_count":47,"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":"2412.02883","title":"TDD-Bench Verified: Can LLMs Generate Tests for Issues Before They Get Resolved?","created":"2024-12-03","cited_by_count":34,"area":null},{"id":"2302.10166","title":"Learning Deep Semantics for Test Completion","created":"2023-02-20","cited_by_count":31,"area":null},{"id":"2310.01602","title":"CAT-LM: Training Language Models on Aligned Code And Tests","created":"2023-10-02","cited_by_count":28,"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":"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":"2404.00566","title":"CodeBenchGen: Creating Scalable Execution-based Code Generation Benchmarks","created":"2024-03-31","cited_by_count":23,"area":null},{"id":"2402.01411","title":"CodePori: Large-Scale System for Autonomous Software Development Using Multi-Agent Technology","created":"2024-02-02","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":"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":"2306.06782","title":"Augmenting Greybox Fuzzing with Generative AI","created":"2023-06-11","cited_by_count":18,"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":"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":"2306.17077","title":"RAPGen: An Approach for Fixing Code Inefficiencies in Zero-Shot","created":"2023-06-29","cited_by_count":14,"area":null},{"id":"2402.05650","title":"Rocks Coding, Not Development--A Human-Centric, Experimental Evaluation of LLM-Supported SE Tasks","created":"2024-02-08","cited_by_count":13,"area":null},{"id":"2310.05727","title":"The Program Testing Ability of Large Language Models for Code","created":"2023-10-09","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":"2403.15756","title":"Leveraging Large Language Models for Preliminary Security Risk Analysis: A Mission-Critical Case Study","created":"2024-03-23","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":"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":"2506.16650","title":"SemAgent: A Semantics Aware Program Repair Agent","created":"2025-06-19","cited_by_count":9,"area":"agents"},{"id":"2302.04048","title":"Automating Code-Related Tasks Through Transformers: The Impact of Pre-training","created":"2023-02-08","cited_by_count":8,"area":null},{"id":"2406.03283","title":"CATCODER: Repository-Level Code Generation with Relevant Code and Type Context","created":"2024-06-05","cited_by_count":8,"area":null},{"id":"2406.06887","title":"$\\textbf{PLUM}$: Improving Code LMs with Execution-Guided On-Policy Preference Learning Driven By Synthetic Test Cases","created":"2024-06-11","cited_by_count":8,"area":"alignment"},{"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":"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":"2308.08033","title":"Domain Adaptation for Code Model-based Unit Test Case Generation","created":"2023-08-15","cited_by_count":7,"area":null},{"id":"2310.07856","title":"Assessing Evaluation Metrics for Neural Test Oracle Generation","created":"2023-10-11","cited_by_count":7,"area":null},{"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":"2206.13619","title":"DeepPERF: A Deep Learning-Based Approach For Improving Software Performance","created":"2022-06-27","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":"2501.11086","title":"Evaluating LLM-Based Regression Test Generation","created":"2025-01-19","cited_by_count":6,"area":null},{"id":"2510.12702","title":"Beyond Postconditions: Can Large Language Models infer Formal Contracts for Automatic Software Verification?","created":"2025-10-14","cited_by_count":6,"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":"2504.01911","title":"Advancing AI-Scientist Understanding: Multi-Agent LLMs with Interpretable Physics Reasoning","created":"2025-04-02","cited_by_count":5,"area":"lr"},{"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":"2411.16927","title":"ASSERTIFY: Utilizing Large Language Models to Generate Assertions for Production Code","created":"2024-11-25","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":"2503.05860","title":"Benchmarking AI Models in Software Engineering: A Review, Search Tool, and Unified Approach for Elevating Benchmark Quality","created":"2025-03-07","cited_by_count":4,"area":null},{"id":"2507.12284","title":"MERA Code: A Unified Framework for Evaluating Code Generation Across Tasks","created":"2025-07-16","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":"2111.04473","title":"Senatus -- A Fast and Accurate Code-to-Code Recommendation Engine","created":"2021-11-05","cited_by_count":3,"area":null},{"id":"2305.13504","title":"Neural Machine Translation for Code Generation","created":"2023-05-22","cited_by_count":3,"area":null},{"id":"2310.00483","title":"Prompting Code Interpreter to Write Better Unit Tests on Quixbugs Functions","created":"2023-09-30","cited_by_count":3,"area":null},{"id":"2403.00338","title":"Semi-Instruct: Bridging Natural-Instruct and Self-Instruct for Code Large Language Models","created":"2024-03-01","cited_by_count":3,"area":"synth"},{"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":"2510.01994","title":"Clarifying Semantics of In-Context Examples for Unit Test Generation","created":"2025-10-02","cited_by_count":3,"area":null},{"id":"2208.13928","title":"Exploring and Evaluating Personalized Models for Code Generation","created":"2022-08-29","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":"2503.23466","title":"Codehacks: A Dataset of Adversarial Tests for Competitive Programming Problems Obtained from Codeforces","created":"2025-03-30","cited_by_count":2,"area":null},{"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":"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":"2601.13097","title":"RM -RF: Reward Model for Run-Free Unit Test Evaluation","created":"2026-01-19","cited_by_count":2,"area":null},{"id":"2602.02079","title":"AICD Bench: A Challenging Benchmark for AI-Generated Code Detection","created":"2026-02-02","cited_by_count":2,"area":null},{"id":"2602.20610","title":"SpecMind: Cognitively Inspired, Interactive Multi-Turn Framework for Postcondition Inference","created":"2026-02-24","cited_by_count":2,"area":null},{"id":"2308.08943","title":"Towards Automatically Addressing Self-Admitted Technical Debt: How Far Are We?","created":"2023-08-17","cited_by_count":1,"area":null},{"id":"2502.02866","title":"A Systematic Approach for Assessing Large Language Models' Test Case Generation Capability","created":"2025-02-05","cited_by_count":1,"area":null},{"id":"2503.05394","title":"Static Program Analysis Guided LLM Based Unit Test Generation","created":"2025-03-07","cited_by_count":1,"area":null},{"id":"2506.17369","title":"Re-Evaluating Code LLM Benchmarks Under Semantic Mutation","created":"2025-06-20","cited_by_count":1,"area":null},{"id":"2509.23812","title":"Navigating the Labyrinth: Path-Sensitive Unit Test Generation with Large Language Models","created":"2025-09-28","cited_by_count":1,"area":null},{"id":"2510.17868","title":"UniCode: Augmenting Evaluation for Code Reasoning","created":"2025-10-16","cited_by_count":1,"area":"lr"},{"id":"2511.20403","title":"LLMs for Automated Unit Test Generation and Assessment in Java: The AgoneTest Framework","created":"2025-11-25","cited_by_count":1,"area":null},{"id":"2602.13723","title":"Compiling Large Multi-Modal Requirement Documents into Runnable Software Systems: From an Agentic Test-Driven Perspective","created":"2026-02-14","cited_by_count":1,"area":"agents"},{"id":"2602.21997","title":"Enhancing LLM-Based Test Generation by Eliminating Covered Code","created":"2026-02-25","cited_by_count":1,"area":null},{"id":"2607.04232","title":"Teaching Code LLMs to Reason with Intermediate Formal Specifications","created":"2026-07-05","cited_by_count":1,"area":"lr"},{"id":"2607.08983","title":"SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation","created":"2026-07-09","cited_by_count":1,"area":"agents"},{"id":"2607.09123","title":"ReProAgent: Tool-Augmented Multi-Stage Agentic Generation of Bug Reproduction Tests from Issue Reports","created":"2026-07-10","cited_by_count":1,"area":"agents"},{"id":"2108.03322","title":"Distilling Transformers for Neural Cross-Domain Search","created":"2021-08-06","cited_by_count":0,"area":null},{"id":"2310.03174","title":"Test Case Recommendations with Distributed Representation of Code Syntactic Features","created":"2023-10-04","cited_by_count":0,"area":null},{"id":"2312.08055","title":"Breaking the Silence: the Threats of Using LLMs in Software Engineering","created":"2023-12-13","cited_by_count":0,"area":null},{"id":"2312.12598","title":"A Case Study on Test Case Construction with Large Language Models: Unveiling Practical Insights and Challenges","created":"2023-12-19","cited_by_count":0,"area":null}],"next_cursor":"100"}