Reproduction test generation translates a natural-language issue description into executable tests that fail on the original code and pass after the issue is resolved, providing executable evidence for verifying candidate patches. Existing benchmarks are constructed for individual programming languages, preventing a un...
Kazuki Kusama, Sota Nakashima, Haruka Tokumasu et al.· 0 citations
It is suggested that TnT-LLM and CLIMB can be used in practical situations in the SE domain, while researchers should first assess the complexity of the generated taxonomies and their cost using a subset of the target data to decide whether to use automated methods or human experts.
Sota Nakashima, Yuta Ishimoto, Masanari Kondo et al.· 0 citations
To ensure the overall quality of AI-enabled software, not only traditional software components but also AI components need to be tested and repaired. Among AI components, Transformer models are increasingly integrated into software systems, which makes their misbehaviors critical. Although prior work in the software en...
Yuta Ishimoto, Paolo Arcaini, Fuyuki Ishikawa et al.· arXiv.org· 0 citations
In recent years, Large Language Models (LLMs) have made significant strides, leading to the emergence of multimodal LLMs capable of processing diverse inputs such as images and audio. Previous research indicates that the supply of multimodal LLMs with combined textual and visual information improves the automatic code...
Yuki Toi, Tao Xiao, Kazushi Tomoto et al.· 0 citations
KLEECopilot, a Large Language Model-guided directed symbolic execution approach built on KLEE, exhibits only marginal sensitivity to model scale, supporting the efficacy of integrating security semantics and loop-exit prioritization.
Lingfeng Chen, Tao Xiao, Masanari Kondo et al.· arXiv.org· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
