TELPA, a novel LLM-based test generation technique, leverages program analysis to enhance the coverage of hard-to-cover branches by extracting real usage scenarios, understanding inter-procedural dependencies, and guiding LLMs with counter-examples.
SymPrompt, a novel code-aware prompting strategy, enables large language models to generate high coverage test suites for complex software units by deconstructing the test generation process into a multi-stage sequence of prompts aligned with the execution paths of the method under test.
Existing developer-written test cases can embed domain knowledge that encodes metamorphic relations (MRs). MR-Scout automatically discovers and synthesizes these encoded MRs from test cases in open-source software projects to enable automated test case generation.
Pre-trained large language models are revolutionizing software testing, offering innovative approaches and addressing key challenges.
Effiziente Mutation Analyse durch Ausführungstaints.
COVERUP is a novel system that significantly improves Python regression test coverage through an iterative, coverage-guided approach using large-language models (LLMs).
COVERUP is a novel system that significantly improves Python regression test coverage by combining coverage analysis and large-language models (LLMs).
Fine-grained assertion-based test selection improves precision and efficiency in regression testing.
Rich-state simulated populations significantly enhance test coverage and fault detection in automated testing at Meta.
提案されたBayesFLoフレームワークは、複雑なソフトウェアシステムのベイジアン障害特定を効率的に行います。