cs.SE · 2026-06-15 · No. 24

Software Engineering, 2026-06-15.

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

01 — The papers

6 entries
  1. 01

    Empowering Student Debugging in Parallel Programming with Execution Traces and Large Language Models

    God'salvation F. Oguibe, Vinodh Kumaran Jayakumar, Tongping Liu, Andrew Lan, Wei Wang

    cs.SE · cs.DC

    Concurrent programming is a core component of Computer Science curricula, yet remains notoriously difficult for students to master due to its inherent complexity and the nondeterministic nature of concurrency bugs such as deadlocks and race conditions. In this work, we present ParaView, an educational tool designed to help students understand, debug, and correct concurrency issues in parallel programs written in C/C++. ParaView provides...

    arxiv.org/abs/2606.14607 · PDF

  2. 02

    Regulating the Machine Contributor: Governance and Policy Alignment in Open Source

    Jassem Manita, Aziz Amari

    cs.SE · cs.AI

    AI-assisted software development has moved from line-level autocomplete to agents that can plan changes, edit files, and submit pull requests with limited human supervision. Open-source software, however, evolves through a process designed for humans: contributor agreements, codes of conduct, and review norms all assume a legally accountable person who can attest to provenance and answer reviewer questions. Autonomous and semi-autonomous AI...

    arxiv.org/abs/2606.14594 · PDF

  3. 03

    When Errors Become Narratives: A Longitudinal Taxonomy of Silent Failures in a Production LLM Agent Runtime

    Wei Wu

    cs.SE · cs.AI · cs.DC

    LLM agent systems increasingly run as long-lived autonomous runtimes: scheduling jobs, calling tools, maintaining memory, and pushing results to humans. We present a longitudinal study of silent failures in one such system: a personal-assistant agent runtime in continuous production since March 2026, with roughly 40 scheduled jobs, 8 LLM providers, a tool-governance proxy, and a knowledge-base memory plane, defended by 4,286 unit tests and...

    arxiv.org/abs/2606.14589 · PDF

  4. 04

    tap: A File-Based Protocol for Heterogeneous LLM Agent Collaboration

    Minseo Kim

    cs.SE · cs.AI · cs.HC

    Existing multi-agent software development systems have proposed many forms of agent collaboration, including role-based collaboration and automated code review. However, many systems assume a common runtime, a central conversation server, or the same API family. Under these assumptions, LLM agents from different vendors cannot easily exchange messages directly from their own execution environments while dividing development and review work on...

    arxiv.org/abs/2606.14445 · PDF

  5. 05

    No Accidental Software Agent First Canonical Code for Human Code Entropy Reduction and 30 to 500 times Lower Frontier Model Requirements

    Jepson Taylor

    cs.SE · cs.AI

    Frontier coding models may spend substantial capacity learning not only program behavior, but also accidental entropy in human repositories. Such repositories contain valuable signals: tests, incidents, migrations, edge cases, product judgment, and operational history. These signals are entangled with framework churn, naming drift, generated-source ambiguity, dependency rituals, CI dialects, weak proof routes, and human-oriented review...

    arxiv.org/abs/2606.14357 · PDF

  6. 06

    I'm Sorry Driver, I'm Afraid I Can't Do That: Appraising the Safety of LLMs within Automotive Contexts

    Shaun Feakins, Ibrahim Habli, Kim Littler, Robert Palin

    cs.SE · cs.AI · cs.ET

    This paper appraises recent frameworks within AI development to integrate LLMs into control tasks in automotive contexts from the perspective of safety assurance. This work has built upon the rapid integration of LLMs across automotive settings. However, we find that at present, these frameworks face significant challenges, limiting their efficacy in real-time safety-critical contexts. Firstly, we consider conceptual challenges, including the...

    arxiv.org/abs/2606.14327 · 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.