Researchers have developed a new methodology for generating executable tests for concurrent stateful Rust APIs using Large Language Models (LLMs). This approach employs Petri nets to represent API resources, lifecycle conditions, and dependencies, enabling the derivation of complex concurrent scenarios. These scenarios serve as a constrained intermediate representation for LLMs, guiding them to synthesize tests that adhere to API preconditions and explore concurrency more effectively. The system includes mechanisms for preserving modeled intent during synthesis and a semantic oracle to distinguish between synthesis failures and API behavior violations. AI
IMPACT Enhances LLM capabilities for generating complex, executable tests for concurrent software systems.
RANK_REASON The cluster contains a research paper detailing a novel methodology for test generation. [lever_c_demoted from research: ic=1 ai=1.0]
- alphaXiv
- arXiv
- CatalyzeX
- DagsHub
- Gotit.pub
- Hugging Face
- Large language models
- Petri net
- Rust
- ScienceCast
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →
