cs.SE · 2026-06-26 · No. 35

Software Engineering, 2026-06-26.

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

    The Spec Growth Engine: Spec-Anchored, Code-Coupled, Drift-Enforced Architecture for AI-Assisted Software Development

    Hartwig Grabowski

    cs.SE · cs.AI

    AI coding agents dramatically accelerate implementation speed but introduce two structural failure modes that existing spec-driven approaches do not fully solve: (1) context explosion -- the agent must reason over an entire repository at once, degrading output quality as the context window fills; and (2) silent spec-code drift -- code evolves, the specification does not, and the divergence becomes invisible until it is costly to repair. We...

    arxiv.org/abs/2606.27045 · PDF

  2. 02

    A Deterministic Control Plane for LLM Coding Agents

    Padmaraj Madatha

    cs.SE · cs.AI · cs.CR

    LLM coding harnesses grant agents broad file and shell access, yet the configuration layer that steers them -- rules files, agent definitions, IDE-specific markdown -- is largely unmanaged. A prevalence study of 10,008 public GitHub repositories (n=6,145 agent config files) finds that agent configurations propagate as undeclared shared components: 10.1% of tracked paths are SHA-256 exact duplicates across independent repositories...

    arxiv.org/abs/2606.26924 · PDF

  3. 03

    Evaluation-Strategy Gap in Fault Diagnosis of Deep Learning Programs

    Sigma Jahan

    cs.SE · cs.AI · cs.LG

    Deep Learning (DL) programs can fail during training for many reasons, and diagnosing the cause is a costly and time-consuming maintenance task. Techniques for diagnosing such failures are commonly assessed using within-program cross-validation, which may be inadequate for deployment settings involving previously unseen programs. It is therefore necessary to assess how performance differs across these settings and to identify the causes of...

    arxiv.org/abs/2606.26492 · PDF

  4. 04

    An Empirical Study of LLM-Generated Specifications for VeriFast

    Wen Fan, Minh Tran, Sanya Dod, Xin Hu, Marilyn Rego, Danning Xie, Jenna DiVincenzo, Lin Tan

    cs.SE · cs.AI · cs.LO · cs.PL

    Static verification tools can assure industrial scale software, but require significant human labor to write specifications. This is particularly true of static verifiers based on separation logic (SL verifiers), which excel at verifying heapmanipulating programs, but require many complex auxiliary specifications to reason about heap structure. Recent work applies large language models (LLMs) to generate code, tests, and proofs, including...

    arxiv.org/abs/2606.26490 · 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.