cs.SE · 2026-08-05 · No. 75

Software Engineering, 2026-08-05.

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

01 — The papers

5 entries
  1. 01

    Can LLMs Test Terminal User Interfaces?

    Chao Peng, Ruida Hu, Ajitha Rajan, Tegawendé F Bissyandé, Jacques Klein, Cuiyun Gao

    cs.SE · cs.AI · cs.LG

    Terminal User Interfaces (TUIs) combine the stateful, screen-oriented behaviour of GUIs with terminal deployment and are now common in developer tools. Yet they lack a dedicated testing methodology. We survey 197 real-world TUI applications: only 12% of test code exercises the interface, and 45% of those tests never send input, checking a static frame instead. We turn these applications into a headless benchmark spanning ratatui/Rust,...

    arxiv.org/abs/2608.03743 · PDF

  2. 02

    Pattern over Pixels: Measuring Pattern Completion Bias in Multimodal Code Generation

    Khai-Nguyen Nguyen, Oscar Chaparro, Antonio Mastropaolo

    cs.SE · cs.AI · cs.CV

    Multimodal large language models (MLLMs) are increasingly used to translate webpage screenshots into front-end code, but repeated UI patterns may sway them toward visually incorrect yet pattern-consistent outputs. In this work, we test how repeated webpage patterns hurt MLLM accuracy on an objective screenshot-to-code fill-in-the-blank task. We introduce the first benchmark for visual pattern-completion bias, where one localized element in a...

    arxiv.org/abs/2608.03691 · PDF

  3. 03

    Leveraging System-Level Observations to Inform Bayesian Learning of Model Parameters for Quantitative Verification

    Simos Gerasimou, Xingyu Zhao

    cs.SE · cs.AI · cs.LO

    Combining Bayesian learning and quantitative verification is a powerful toolset for analysing key quantitative properties of software systems, like reliability and response time. However, the accuracy and robustness of verification results strongly depend on the prior knowledge (PK) underlying Bayesian inference. This knowledge reflects original beliefs about the probability of events and typically depends on domain expertise. Using...

    arxiv.org/abs/2608.03489 · PDF

  4. 04

    Route-Align-Verify for Functional Correctness in Code Generation

    Erxue Zhou, Jingxiang Meng, Aofan Liu

    cs.SE · cs.AI

    Large language models (LLMs) have substantially improved code generation, yet achieving strong functional correctness remains difficult, especially for heterogeneous programming tasks where a single prompting strategy and a single directly generated output are often insufficient. In this paper, we present RAV, a lightweight and modular framework that improves code generation with a fixed backbone model through three coordinated stages: Route,...

    arxiv.org/abs/2608.03341 · PDF

  5. 05

    Evaluating LLM Trade-offs for Enterprise Automation: Lessons from Workflow Generation in a Production Enterprise Platform

    Xavier Wrenn, Radoslav Raykov, Aleksandar Angelov, Hirokuni Kitahara, Yuji Watanabe, Anca Sailer

    cs.SE · cs.AI

    Enterprise compliance management requires rapid adaptation to evolving regulatory frameworks (e.g., DORA, AI RMF, FedRAMP) and tight remediation SLAs. Traditional static orchestrators often fail in hybrid cloud environments where event-driven assessments demand that automation code adapt to runtime context in seconds. This paper presents lessons learned from evaluating six large language models for AI-driven workflow generation in a...

    arxiv.org/abs/2608.03311 · 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.