cs.SE · 2026-07-05 · No. 44

Software Engineering, 2026-07-05.

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

01 — The papers

7 entries
  1. 01

    TestEvo-Bench: An Executable and Live Benchmark for Test and Code Co-Evolution

    Jiale Amber Wang, Kaiyuan Wang, Pengyu Nie

    cs.SE · cs.AI · cs.CL

    Software tests and code evolve together: a code change should be followed by new or updated tests that record the new software behavior. Yet existing test generation and update benchmarks often isolate the test from the code change, and rely on static metadata that does not verify whether a test is executable or semantically tied to the code change. This makes it difficult to evaluate whether a test automation agent understands how a code...

    arxiv.org/abs/2607.02469 · PDF

  2. 02

    Reasoning effort, not tool access, buys first-try reliability in agentic code generation: an observational study

    Achint Mehta

    cs.SE · cs.AI

    Agentic coding assistants are increasingly given extra capabilities, such as browser based testing tools and design oriented system prompts, on the assumption that more capability yields better software. This study tested that assumption directly. Ninety independent agent runs built the same application, a real time retrospective board, from one detailed specification, each scored on a fixed 14 criterion functional rubric (42 point maximum)...

    arxiv.org/abs/2607.02436 · PDF

  3. 03

    Understanding Agent-Based Patching of Compiler Missed Optimizations

    Batu Guan, Zirui Wang, Shaohua Li

    cs.SE · cs.AI

    Compiler missed optimizations refer to cases in which compilers failed to optimize certain code. It takes many compiler developers' efforts to implement or patch such missed optimizations. In this paper, we present a systematic study of how well agents patch compiler missed optimizations. We identify a significant challenge that patching a missed optimization requires more than just fixing the reported case, and instead requires generalizing...

    arxiv.org/abs/2607.02370 · PDF

  4. 04

    SkillFuzz: Fuzzing Skill Composition for Implicit Intents Discovery in Open Skill Marketplaces

    Jinwei Hu, Yi Dong, Youcheng Sun, Xiaowei Huang

    cs.SE · cs.AI · cs.CL

    Large Language Model (LLM)-based agents increasingly automate software engineering tasks through reusable skills, natural-language instruction documents that guide planning and execution. Open skill marketplaces enable users to assemble agents by co-activating community-contributed skills, but marketplace operators typically audit skills in isolation. As a result, individually benign skills may interact to redirect an agent toward unintended...

    arxiv.org/abs/2607.02345 · PDF

  5. 05

    Prompt Coverage Adequacy

    Florian Tambon, Michael Konstantinou, Cedric Richter, Charles Chenouard, Mark Harman, Mike Papadakis

    cs.SE · cs.AI

    In recent years, it has become increasingly evident that large language models (LLMs) and autonomous agents raise the level of abstraction in software development by shifting the focus from writing precise procedures to expressing intents and goals. This paradigm shift introduces new challenges, particularly in how testing should be guided when prompts, rather than code, become primary development artifacts. To address this challenge, we...

    arxiv.org/abs/2607.02057 · PDF

  6. 06

    An Exploratory Study on LLM-Generated Code and Comments in Code Repositories

    Yongyi Ji, Jiaji Wang, Yi Zhou, Fuxiang Chen, Hongji Yang

    cs.SE · cs.AI

    The use of LLMs in software development has become increasingly widespread on tasks such as code generation and summarization. Reports from large technology companies showed that around 20% to 30% of their code are generated by LLMs. However, there remains skepticism about the practical usage of LLM-generated code and comments, such as concerns on more time for debugging the generated code and the unnaturalness of the generated comments. In...

    arxiv.org/abs/2607.01867 · PDF

  7. 07

    Decoupling Code Complexity from Newcomer Participation: A Causal Study of AI Coding Agent Adoption in OSS

    Weiwei Xu, Xuanning Cui, Hengzhi Ye, Minghui Zhou

    cs.SE · cs.AI

    Open-source projects depend on a steady inflow of newcomers. A growing concern is that AI coding agents (tools such as Cursor and Claude Code that write code from natural-language instructions) will crowd them out, by absorbing the simple tasks that beginners start with and by making code harder to read. We give this concern a causal answer. Using GitHub code search we identify 1,888 projects that adopted an agent, signaled by their first...

    arxiv.org/abs/2607.01810 · 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.