{"total":16,"rows":[{"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":"2503.05012","title":"LLMs' Reshaping of People, Processes, Products, and Society in Software Development: A Comprehensive Exploration with Early Adopters","created":"2025-03-06","cited_by_count":8,"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":"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":"2509.25043","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":"2608.23961","title":"Evaluating Language Models on Cross-Language Code Functional Equivalence","created":"2026-08-25","cited_by_count":2,"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":"2510.17163","title":"TREAT: A Code LLMs Trustworthiness / Reliability Evaluation and Testing Framework","created":"2025-10-20","cited_by_count":1,"area":null},{"id":"2410.08911","title":"Test-driven Software Experimentation with LASSO: an LLM Prompt Benchmarking Example","created":"2024-10-11","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":"2606.19725","title":"Library-Aware Doubles and Iterative Repair for Large Language Model-Generated Unit Tests in OpenSIL Firmware","created":"2026-06-18","cited_by_count":0,"area":null},{"id":"2607.22880","title":"Do Coverage and Mutation Scores of LLM-Generated Test Suites Correlate with Their Effectiveness? (Replicability Study)","created":"2026-07-24","cited_by_count":0,"area":null},{"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":"2608.19475","title":"Measuring What a Specification Determines: A Formal Semantic-Block Model and an Execution-Judged Benchmark","created":"2026-08-19","cited_by_count":0,"area":null}],"next_cursor":null}