Formal verification of Rust programs with Verus provides strong correctness guarantees, but developing the auxiliary specifications and proofs still requires considerable manual effort. Existing LLM-based proof-synthesis agents can automate part of this process, yet their effectiveness on non-trivial tasks is often lim...
Yu-Cheng Zhang, Cheng Wen, Jia-Lun Cao et al.· Proceedings of the 41st IEEE...· 0 citations
Formal verification provides strong correctness guarantees, but its practical adoption is limited by the cost of writing precise formal specifications. While large language models can generate candidate specifications, prompt-only generation and monolithic LLM pipelines often struggle with verifier feedback, iterative...
Wen-Jie Wu, Jun-Jie Hu, Cheng Wen et al.· Companion Proceedings of the...· 0 citations
Automated unit test generation promises to reduce the cost of software quality assurance, and hence, is attracting attention from both academia and industry. Yet, generating assertions that are executable, meaningful to developers, and able to catch faults remains an unsolved challenge. Existing approaches either rando...
Jia-Lun Cao, Hao-Yu Wang, Hao-Ran Yan et al.· Proceedings of the ACM on So...· 0 citations
The first empirical study focused on agent-reactive (AR) bugs is conducted, constructing a two-axis taxonomy covering observable symptoms and the LLM behaviors that trigger them and highlights challenges specific to LLM agents.
