It is shown that existing approaches still struggle to correctly generate complete code fragments across granularities and languages, and method rankings also vary across task granularities and programming languages, highlighting the importance of multilingual, multi-granularity evaluation for comprehensively assessing...
Bo-Wen Yang, Jia-Jun Jiang, Lu-Xue Yu et al.· 0 citations
AnchorRepair is proposed, a dual-agent framework that treats the Java source as first-class diagnostic evidence that generalizes across LLM backends without modification and achieves repair coverage comparable to a general-purpose coding agent at less than half the cost.
Jia-Jun Sun, Yao-Cai Zhao, Feng-Jie Li et al.· 0 citations
A large-scale empirical study comparing representative code translation techniques across methodological paradigms and translation granularities, which shows that LLMs and LLM-based methods generally outperform learning-based methods in method-level correctness, although similarity metrics alone do not reliably reflect...
Ruihan Fan, Jia-Jun Jiang, Xin-Peng Wang et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
