cs.SE · 2026-07-13 · No. 52

Software Engineering, 2026-07-13.

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

01 — The papers

9 entries
  1. 01

    Failure as a Process: An Anatomy of CLI Coding Agent Trajectories

    Xiangxin Zhao, Han Li, Shuaiting Li, Tianyi Zhao, Earl T. Barr, Federica Sarro, He Ye

    cs.SE · cs.AI

    Large language model (LLM) coding agents are increasingly deployed to autonomously perform software engineering tasks in terminal-based environments, making their reliability a growing concern. Existing empirical studies investigate why coding agents fail, yet they largely treat failure as a final outcome rather than a temporal process, providing limited insight into how failures emerge, evolve, and become unrecoverable. We present the first...

    arxiv.org/abs/2607.09510 · PDF

  2. 02

    Practical Source Code Recovery from Binary Functions Using Anchor-Based Retrieval and LLM Reasoning

    Charles Edward Gagnon, Steven H. H. Ding, Philippe Charland, Benjamin C. M. Fung

    cs.SE · cs.AI

    We present a practical pipeline for recovering source code from stripped binary functions by combining reverse engineering, anchor-based source code retrieval, and large language model reasoning. Our binary-to-source-code retrieval method attempts to identify the source function from a source code database, rather than generating approximate decompiled pseudocode. It extracts anchors such as strings, constants, external calls, and available...

    arxiv.org/abs/2607.09452 · PDF

  3. 03

    Diversifying to Verify: When Task-Equivalent Programs Differ in Verifiability

    Shirley Yu, Ruben Martins

    cs.SE · cs.AI · cs.LO

    Program verification is crucial for software correctness, but producing fully verified programs remains difficult in practice. This paper studies whether implementation structure affects automated verifiability when multiple generated programs are intended to satisfy the same task-level semantics. We present Diversify2Verify, a staged LLM-based pipeline for Why3 that infers representation-specific contracts, generates and tests diverse...

    arxiv.org/abs/2607.09366 · PDF

  4. 04

    Git-Assistant: Planning-Based Support for Updating Git Repositories

    Alfredo Garrachón Ruiz, Tomás de la Rosa, Daniel Borrajo

    cs.SE · cs.AI · cs.CL

    Version control systems are essential for collaborative software development, yet tools like git remain challenging for many practitioners. Recent advances in Large Language Models (LLMs) offer promising capabilities for interpreting developer intent, but their effectiveness in repository management tasks is limited by the need for formal reasoning. This work introduces Git-Assistant, an AI-based assistant that combines LLMs with automated...

    arxiv.org/abs/2607.09224 · PDF

  5. 05

    Attention to Detail: Evaluating Energy, Performance, and Accuracy Trade-offs Across vLLM Configurations

    Nada Zine, Tristan Coignion, Vincenzo Stoico, Clément Quinton, Romain Rouvoy, Patricia Lago

    cs.SE · cs.AI · cs.PF

    Large Language Models are reshaping how software is developed and maintained. They are typically deployed in production using inference engines such as vLLM, which can efficiently serve pre-trained, highly configurable models. While prior work has focused on model architectures and hardware acceleration, the impact of inference engine configuration on energy consumption, performance, and output quality remains poorly understood. In this...

    arxiv.org/abs/2607.09172 · PDF

  6. 06

    Inside the Skill Market: From Software Engineering Activities to Reusable Agent Skills

    Jialun Cao, Xinru Yan, Songqiang Chen, Yaojie Lu, Zhongxin Liu, Shing-Chi Cheung

    cs.SE · cs.AI

    Software engineering (abbrev. SE) has continuously evolved through increasingly powerful forms of reuse, from source code and libraries to components and services. Recent advances in AI agents have introduced a potentially new reusable artifact: skills. Emerging agent skill repositories and marketplaces enable developers to package, share, and reuse SE expertise as reusable skills. This trend raises a fundamental question: what SE activities...

    arxiv.org/abs/2607.09065 · PDF

  7. 07

    SCATE: Learning to Supervise Coding Agents for Cost-Effective Test Generation

    Sijia Gu, Noor Nashid, Ali Mesbah

    cs.SE · cs.AI

    While autonomous coding agents have significantly advanced automated test generation, they remain fundamentally limited by lazy generation, a phenomenon where agents prematurely terminate tasks and systematically avoid complex programmatic logic, resulting in inadequate code coverage. Currently, mitigating this premature termination requires continuous human-in-the-loop supervision. This heavy reliance on human intuition creates a bottleneck...

    arxiv.org/abs/2607.08983 · PDF

  8. 08

    The Patchwork Problem in LLM-Generated Code

    Viraaji Mothukuri, Reza M. Parizi

    cs.SE · cs.AI

    LLM-generated code often compiles, passes tests, and appears correct, yet breaks once deployed. The root cause is frequently structural rather than logical. A generated endpoint references configuration keys never declared in the project, an import targets a package that does not exist in any registry, or a new route omits the authentication guard applied to every sibling endpoint. Each patch is locally valid but globally incoherent, and...

    arxiv.org/abs/2607.08981 · PDF

  9. 09

    ProjAgent: Procedural Similarity Retrieval for Repository-Level Code Generation

    QiHong Chen, Aaron Imani, Iftekhar Ahmed

    cs.SE · cs.AI · cs.IR

    Repository-level code generation requires implementing target functions while accounting for complex cross-file dependencies and project-specific conventions. Existing retrieval methods predominantly rely on lexical, structural, or semantic similarity, often overlooking repository functions that implement similar procedural logic despite differing in identifiers or application domains. We propose ProjAgent, a repository-level code generation...

    arxiv.org/abs/2607.08691 · 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.