الباحثون

Yongmin Li

المنشورات 2

نسخة أولية وصول مفتوح

CONTRA: Discovering and Qualifying Behavior-Changing Questions for Selective Clarification in LLM Code Generation

Zheng Fang, Yongmin Li, Yichang Zhang وآخرون · 2026

Coding agents can generate code that appears correct but implements behavior the user never intended. This mismatch can arise when an agent silently resolves underspecified requirements through its own assumptions. As subsequent development builds on these assumptions, correcting the resulting behavior can become incre …

نسخة أولية وصول مفتوح

Self-Spec Verifiable Code Generation

Jiaru Qian, Yihong Dong, Yongmin Li وآخرون · 2026

Large language models (LLMs) may generate unreliable code on corner cases missed by testing, while formal verification can provide machine-checkable guarantees. Recently, researchers have proposed several benchmarks to evaluate the capabilities of LLMs in generating formally verifiable code, where LLMs need to formulat …

المؤلفون المشاركون