3 papers
cs.SE2026
Archer: Towards Agentic Review for Compiler Optimizations
Yunbo Ni, Shaohua Li
Modern compilers are frequently updated, but expert review capacity is highly limited, leading to delayed integration and, in some cases, subtle semantic bugs entering the compiler…
cs.SE2025
Interleaving Large Language Models for Compiler Testing
Yunbo Ni, Shaohua Li
Testing compilers with AI models, especially large language models (LLMs), has shown great promise. However, current approaches struggle with two key problems: The generated progra…
cs.PL2025
An Empirical Study of Rust-Specific Bugs in the rustc Compiler
Zixi Liu, Yang Feng, Yunbo Ni +5
Rust is gaining popularity for its well-known memory safety guarantees and high performance, distinguishing it from C/C++ and JVM-based languages. Its compiler, rustc, enforces the…