cs.SE · 2026-07-21 · No. 60

Software Engineering, 2026-07-21.

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

    TRIM: Reducing AI-Generated CodeSlop via Agent Trajectory Minimization

    Alex Mathai, Shobini Iyer, Aleksandr Nogikh, Petros Maniatis, Franjo Ivancic, Junfeng Yang, Baishakhi Ray

    cs.SE · cs.AI · cs.OS

    Coding agents are increasingly used to accelerate code generation in many downstream tasks, such as fixing bugs, building applications, and prototyping. However, despite their value as coding assistants, agent-generated code tends to be larger and more verbose than the corresponding human-written implementation. In this work, we show that the cause lies in the agent's own search process: while iterating toward a passing solution, an agent...

    arxiv.org/abs/2607.18161 · PDF

  2. 02

    Autoresearch with Coding Agents: Generalizers and Metric-Maximizers on Quran Recitation Data

    Nursultan Askarbekuly, Mohamad Al Mdfaa, Ahmed Helaly, Gonzalo Ferrer, Manuel Mazzara

    cs.SE · cs.AI

    Coding agents can now be left alone to improve software against a score. In this pattern--recently popularized as "autoresearch"--the agent receives a dataset, an evaluation script, and one editable file, and iterates without supervision: modify the code, measure, keep the change if the score improves. But what does the agent actually optimize--the developer's intent, or the literal number? We ran this loop on a real production task: deciding...

    arxiv.org/abs/2607.18064 · PDF

  3. 03

    Persona-as-Configuration: Generative Stakeholder Reporting for Agricultural Floods

    Oliver Aleksander Larsen, Tiziano Santilli, Francesco Daghero, Mahyar T. Moghaddam

    cs.SE · cs.AI · cs.HC

    Cyber-physical systems built on deterministic edge inference, such as on-vehicle flood detection for agricultural fields, produce structured decision logs that must be interpreted differently by heterogeneous stakeholders. Pairing such systems with large language models (LLMs) to generate stakeholder-specific reports introduces a tension: the generative layer is non-deterministic, while the edge plane must remain replayable and auditable. We...

    arxiv.org/abs/2607.17774 · PDF

  4. 04

    Integrating High-Level Requirements to Low-Level Tests with Machine-Readable V&V Specifications

    Mansur Arief, Nur Ahmad Khatim, Ali Akarma, Ahmad Alfan Alfian Irfan

    cs.SE · cs.AI

    Modern software teams have mature tools for low-level testing, such as pytest, JUnit, and Jest, which make it inexpensive to write unit tests and run them on every commit. Systems engineering, in parallel, has developed rigorous principles for design verification and validation (V&V), which has worked very well across engineering discipline to align user expecations and requirements with developers' deliverables. In practice, however, the two...

    arxiv.org/abs/2607.17686 · PDF

  5. 05

    CommitLLM: A Fine-Tuned Pipeline for Git Commit Message Generation

    Md Rafid Haque, Poojan Narendrabhai Patel, Meetkumar Vijaybhai Raychura

    cs.SE · cs.AI

    Developers frequently write uninformative git commit messages such as "fix" or "update stuff", degrading the value of version-control history for code review, debugging, and onboarding. We present CommitLLM, a three-stage pipeline that generates concise, Conventional Commits-compliant messages from code diffs using a fine-tuned small language model. The system combines (1) QLoRA fine-tuning of Mistral-7B-Instruct-v0.2 on the CommitPackFT...

    arxiv.org/abs/2607.17532 · 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.