cs.SE · 2026-08-13 · No. 83

Software Engineering, 2026-08-13.

4 new papers in cs.SE. Titles, authors, abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →

01 — The papers

4 entries
  1. 01

    ADEPT: A Unified Framework for Deep Learning Test Adequacy

    Yidi Kao, Shawn Burnham, Tommi Rose Fahy, Ali Ghanbari

    cs.SE · cs.LG

    Over the past decade, many test adequacy metrics have been proposed for deep learning that characterize test dataset adequacy from different perspectives, e.g., neuron activation behavior, latent feature coverage, decision-boundary exploration, etc. However, these metrics are typically released as independent research prototypes with substantially different installation and preprocessing requirements, execution workflows, and configuration...

    arxiv.org/abs/2608.12144 · PDF

  2. 02

    From Safety Documentation to Safety Knowledge Support: An Evidence-Grounded LLM Framework for Medical Devices

    Tuhinangshu Gangopadhyay, Rasmus Adler, Peter Liggesmeyer, Jan Reich

    cs.SE · cs.AI

    Medical devices are becoming more software-intensive, connected, and AI-enabled. Their development requires risk-management evidence aligned with ISO 14971 and, for software, IEC 62304. This evidence must be kept consistent across requirements, design decisions, software changes, verification results, complaints, and post-market data. These tasks are costly and depend on scarce safety and domain experts. Large language models (LLMs) may...

    arxiv.org/abs/2608.12025 · PDF

  3. 03

    RealisticTritonBench: A Benchmark for Triton-Kernel Generation in Real-World AI Frameworks

    Jinjun Huang, Zhongzhen Wen, Tongtong Xu, Meng Yan, Xin Xia, Zhongxin Liu

    cs.SE · cs.AI

    In modern AI frameworks, GPU kernels are key to overall system performance. Combining usability, portability, and near-handwritten CUDA performance, Triton is widely adopted for implementing GPU kernels. Recent advances show the potential of large language models (LLMs) to automatically generate Triton kernels, reducing the manual effort required from expert kernel developers. Several benchmarks evaluate LLM-generated Triton kernels. However,...

    arxiv.org/abs/2608.12004 · PDF

  4. 04

    Instruction Alignment for Binary Code Representation Learning

    Huaijin Wang, Shuai Wang

    cs.SE · cs.AI · cs.CR

    Binary code representation learning is a fundamental problem in software security and reverse engineering. Existing methods mainly learn function-level embeddings that capture coarse-grained semantic relationships between binary functions, but they largely ignore fine-grained instruction-level correspondences. This limitation misses valuable supervision signals available from compiler debug information, which can support the learning of more...

    arxiv.org/abs/2608.11766 · PDF

This edition is part of The Daily Abstract — cs.SE archive. Subscribe to receive these in your inbox each morning, automatically translated to Spanish, with reply-to-PDF: arxivdaily.ignorelist.com.

Colophon Set in Georgia, with system sans for interface chrome and a monospaced stack for code and paper identifiers. Sole accent: amber #D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.