{"total":75,"rows":[{"id":"2403.17134","title":"RepairAgent: An Autonomous, LLM-Based Agent for Program Repair","created":"2024-03-25","cited_by_count":232,"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":"2504.08703","title":"SWE-PolyBench: A multi-language benchmark for repository level evaluation of coding agents","created":"2025-04-11","cited_by_count":85,"area":"agents"},{"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":"2403.16218","title":"CoverUp: Effective High Coverage Test Generation for Python","created":"2024-03-24","cited_by_count":38,"area":null},{"id":"2502.14948","title":"Learning to Solve and Verify: A Self-Play Framework for Code and Test Generation","created":"2025-02-20","cited_by_count":35,"area":"synth"},{"id":"2507.10535","title":"CodeJudgeBench: Benchmarking LLM-as-a-Judge for Coding Tasks","created":"2025-07-14","cited_by_count":33,"area":null},{"id":"2508.11126","title":"AI Agentic Programming: A Survey of Techniques, Challenges, and Opportunities","created":"2025-08-15","cited_by_count":28,"area":"agents"},{"id":"2501.12862","title":"Mutation-Guided LLM-based Test Generation at Meta","created":"2025-01-22","cited_by_count":25,"area":null},{"id":"2406.07737","title":"The Future of AI-Driven Software Engineering","created":"2024-06-11","cited_by_count":23,"area":null},{"id":"2510.04905","title":"Retrieval-Augmented Code Generation: A Survey with Focus on Repository-Level Approaches","created":"2025-10-06","cited_by_count":23,"area":"rag"},{"id":"2503.21557","title":"debug-gym: A Text-Based Environment for Interactive Debugging","created":"2025-03-27","cited_by_count":19,"area":"agents"},{"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":"2511.02108","title":"Metamorphic Testing of Large Language Models for Natural Language Processing","created":"2025-11-03","cited_by_count":12,"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":"2411.00932","title":"LLMs: A Game-Changer for Software Engineers?","created":"2024-11-01","cited_by_count":11,"area":null},{"id":"2508.21107","title":"Learning to Generate Unit Test via Adversarial Reinforcement Learning","created":"2025-08-28","cited_by_count":11,"area":"lr"},{"id":"2503.15554","title":"Rethinking the Evaluation of Secure Code Generation","created":"2025-03-18","cited_by_count":10,"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":"2503.13580","title":"LLM Test Generation via Iterative Hybrid Program Analysis","created":"2025-03-17","cited_by_count":9,"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":"2409.19019","title":"RAGProbe: An Automated Approach for Evaluating RAG Applications","created":"2024-09-24","cited_by_count":7,"area":"rag"},{"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":"2501.11086","title":"Evaluating LLM-Based Regression Test Generation","created":"2025-01-19","cited_by_count":6,"area":null},{"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":"2502.18473","title":"Disproving Program Equivalence with LLMs","created":"2025-02-05","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":"2404.10678","title":"Automating REST API Postman Test Cases Using LLM","created":"2024-04-16","cited_by_count":4,"area":null},{"id":"2505.02502","title":"Unveiling the Landscape of LLM Deployment in the Wild: An Empirical Study","created":"2025-05-05","cited_by_count":4,"area":null},{"id":"2601.03556","title":"Do Autonomous Agents Contribute Test Code? A Study of Tests in Agentic Pull Requests","created":"2026-01-07","cited_by_count":4,"area":"agents"},{"id":"2408.07106","title":"\"You still have to study\" -- On the Security of LLM generated code","created":"2024-08-13","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":"2511.16383","title":"An Agent-Based Framework for the Automatic Validation of Mathematical Optimization Models","created":"2025-11-20","cited_by_count":3,"area":"agents"},{"id":"2404.09249","title":"Test Code Generation for Telecom Software Systems using Two-Stage Generative Model","created":"2024-04-14","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":"2412.14137","title":"Design choices made by LLM-based test generators prevent them from finding bugs","created":"2024-12-18","cited_by_count":2,"area":null},{"id":"2506.11153","title":"QiMeng-MuPa: Mutual-Supervised Learning for Sequential-to-Parallel Code Translation","created":"2025-06-11","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":"2509.25043","title":"Large Language Models for Software Testing: A Research Roadmap","created":"2025-09-29","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":"2603.23443","title":"Evaluating LLM-Based Test Generation Under Software Evolution","created":"2026-03-24","cited_by_count":2,"area":null},{"id":"2408.12125","title":"AutoTest: Evolutionary Code Solution Selection with Test Cases","created":"2024-08-22","cited_by_count":1,"area":null},{"id":"2504.08113","title":"Test Amplification for REST APIs via Single and Multi-Agent LLM Systems","created":"2025-04-10","cited_by_count":1,"area":"agents"},{"id":"2504.16472","title":"Harden and Catch for Just-in-Time Assured LLM-Based Software Testing: Open Research Challenges","created":"2025-04-23","cited_by_count":1,"area":null},{"id":"2505.12006","title":"SOCIA-$\\nabla$: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation","created":"2025-05-17","cited_by_count":1,"area":"agents"},{"id":"2505.13553","title":"Towards Functional Correctness of Large Code Models with Selective Generation","created":"2025-05-19","cited_by_count":1,"area":null},{"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":"2601.12146","title":"From LLMs to Agents in Programming: The Impact of Providing an LLM with a Compiler","created":"2026-01-17","cited_by_count":1,"area":"agents"},{"id":"2601.22832","title":"Just-in-Time Catching Test Generation at Meta","created":"2026-01-30","cited_by_count":1,"area":null},{"id":"2606.15828","title":"Configuration Smells in AGENTS.md Files: Common Mistakes in Configuring Coding Agents","created":"2026-06-14","cited_by_count":1,"area":"agents"},{"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":"2609.04681","title":"Beyond Code Generation: Reliability, Verification, and Cost Economics in the Agentic Software Development Lifecycle","created":"2026-09-04","cited_by_count":1,"area":"agents"},{"id":"2404.01754","title":"Peer-aided Repairer: Empowering Large Language Models to Repair Advanced Student Assignments","created":"2024-04-02","cited_by_count":0,"area":null},{"id":"2503.17837","title":"A Study on the Improvement of Code Generation Quality Using Large Language Models Leveraging Product Documentation","created":"2025-03-22","cited_by_count":0,"area":null},{"id":"2506.11081","title":"SAGE:Specification-Aware Grammar Extraction for Automated Test Case Generation with LLMs","created":"2025-06-04","cited_by_count":0,"area":null},{"id":"2506.11559","title":"Leveraging GPT-4 for Vulnerability-Witnessing Unit Test Generation","created":"2025-06-13","cited_by_count":0,"area":null},{"id":"2509.15366","title":"Diagnostics of cognitive failures in multi-agent expert systems using dynamic evaluation protocols and subsequent mutation of the processing context","created":"2025-09-18","cited_by_count":0,"area":"agents"},{"id":"2510.18551","title":"SOCIA-Nabla: Textual Gradient Meets Multi-Agent Orchestration for Automated Simulator Generation","created":"2025-10-21","cited_by_count":0,"area":"agents"},{"id":"2510.27417","title":"Agentic LLMs for REST API Test Amplification: A Comparative Study Across Cloud Applications","created":"2025-10-31","cited_by_count":0,"area":"agents"},{"id":"2511.04153","title":"BAPPA: Benchmarking Agents, Plans, and Pipelines for Automated Text-to-SQL Generation","created":"2025-11-06","cited_by_count":0,"area":"agents"},{"id":"2512.01010","title":"Chain of Unit-Physics: A Primitive-Centric Approach to Scientific Code Synthesis","created":"2025-11-30","cited_by_count":0,"area":"agents"},{"id":"2512.01232","title":"LLM-as-a-Judge for Scalable Test Coverage Evaluation: Accuracy, Operational Reliability, and Cost","created":"2025-12-01","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":"2601.18241","title":"TAM-Eval: Evaluating LLMs for Automated Unit Test Maintenance","created":"2026-01-26","cited_by_count":0,"area":null},{"id":"2602.16671","title":"SPARC: Scenario Planning and Reasoning for Automated C Unit Test Generation","created":"2026-02-18","cited_by_count":0,"area":"lr"},{"id":"2604.01442","title":"Fuzzing with Agents? Generators Are All You Need","created":"2026-04-01","cited_by_count":0,"area":"agents"},{"id":"2604.14590","title":"AgileLog: A Forkable Shared Log for Agents on Data Streams","created":"2026-04-16","cited_by_count":0,"area":"agents"},{"id":"2605.01471","title":"Practical Limits of Autonomous Test Repair: A Multi-Agent Case Study with LLM-Driven Discovery and Self-Correction","created":"2026-05-02","cited_by_count":0,"area":"agents"},{"id":"2607.18057","title":"Test Coverage Analysis of Agentic Pull Requests","created":"2026-07-20","cited_by_count":0,"area":"agents"},{"id":"2607.21832","title":"How Do AI Coding Agents Contribute to Software Development? an Empirical Study of Agentic Pull Requests","created":"2026-07-23","cited_by_count":0,"area":"agents"},{"id":"2607.22883","title":"Evaluating and Mitigating the Misguidance Effect of Buggy Code in LLM-Generated Unit Tests","created":"2026-07-24","cited_by_count":0,"area":null},{"id":"2607.28271","title":"Agentic Method for Deterministic Validation of Legacy Code Migration","created":"2026-07-30","cited_by_count":0,"area":"agents"},{"id":"2610.15964","title":"Small but Mighty: Test Suites as Improvement Signals for Self-Evolving Agents","created":"2026-10-11","cited_by_count":0,"area":"agents"},{"id":"2610.18004","title":"SWEPatchTest: Evaluating Software Tests Beyond Reproduction","created":"2026-10-13","cited_by_count":0,"area":"agents"}],"next_cursor":null}