cs.SE · 2026-08-02 · No. 72

Software Engineering, 2026-08-02.

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

    Change2Task: From Repository Changes to Executable Coding Agent Tasks and Environments

    Haomin Qi, Xingliang Wang, Xuanqi Gao, Baihui Sang, Xin Zhang, Minghua Ma, Pengfei Gao, Yu Kang, Qingwei Lin,...

    cs.SE · cs.CL · cs.LG

    Scaling coding agents requires a continuing supply of executable data for training, benchmarking, and continuous evaluation. Each task must couple a realistic software state with a specification, development tools, and reliable verification. To expand this supply, we present Change2Task, a system grounded in repository history that converts merged pull requests into verified tasks on healthy modern revisions of the same repository. It aligns...

    arxiv.org/abs/2607.28591 · PDF

  2. 02

    PAIChecker: Uncovering and Checking PR-Issue Misalignment in SWE-Bench-Like Benchmarks

    Manyi Wang, Junjielong Xu, Pinjia He

    cs.SE · cs.AI

    SWE-bench-like benchmarks are widely used for evaluating LLM's issue resolution capability. They typically follow a common construction pipeline: each PR (Pull Request) is paired with its linked issue by extracting issue references from the PR description; the issue description is used as the problem statement, and the PR patch serves as the test oracle. However, due to the inherent complexity of developing and maintaining large repositories,...

    arxiv.org/abs/2607.28587 · PDF

  3. 03

    From Textual Requirements to Microservice Architectures - A Comprehensive Evaluation of LLM-Based Design Synthesis

    Danyllo Albuquerque, José Renan, Guillermo Rodríguez, Guillermo Rodríguez, Emanuel Dantas, Ademar França, Mirko...

    cs.SE · cs.AI

    Microservice architectures have become dominant for modernizing monolithic systems, yet identifying appropriate services remains challenging and largely manual. Existing decomposition approaches are predominantly code-centric, limiting applicability in early design stages where only textual requirements are available. Despite advances in Large Language Models (LLMs), limited empirical evidence exists on their ability to synthesize complete...

    arxiv.org/abs/2607.28307 · PDF

  4. 04

    Agentic Method for Deterministic Validation of Legacy Code Migration

    Andras Ferenczi, Jordan Docherty, Mariya Bessonov, Matthew Findlay, Krishna Lingamneni

    cs.SE · cs.AI

    Migration of legacy COBOL programs to Java requires extensive testing to ensure correct functionality. This effort is often complicated by the lack of test data and the difficulty of validating all corner cases. In this paper we propose a novel agentic test-synthesis method, the "Locksmith Loop," which is initiated by preparing two runtime environments: the COBOL source and the generated Java target are each instrumented with mocks and...

    arxiv.org/abs/2607.28271 · PDF

  5. 05

    Agentic Metaverse Services: A New As-a-Service Paradigm

    Xiaofei Xu, Quan Z. Sheng, Zhongjie Wang, Boualem Benatallah, Xiao Wang, Ruipeng Han

    cs.SE · cs.AI · cs.MA

    Generative Artificial Intelligence (GenAI) is reconstructing the digital virtual world, upgrading agents through enhancing their abilities in autonomous learning, multi-modal interaction, content generation, and collaborative decision-making. In particular, the shift from conversational chatbots to agentic AI, the most recent significant technical breakthrough of GenAI, has brought a new form of services, agentic services and...

    arxiv.org/abs/2607.28242 · PDF

  6. 06

    Integrating AI into Requirements Quality Learning in Software Engineering Education: A TPACK-Guided Empirical Study

    Hansika Ekanayake Mudiyanselage, Rohan Jai Dharmaraj, Malik Abdul Sami, Zheying Zhang

    cs.SE · cs.AI

    The rapid adoption of generative Artificial Intelligence (AI) in software engineering (SE) practice creates a need for pedagogically grounded approaches to AI integration in SE education, especially in conceptually intensive subjects such as requirements engineering (RE). This study examines a TPACK-guided integration of a multi-agent AI tool into a master-level RE assignment on requirements quality analysis. Using a mixed-methods design...

    arxiv.org/abs/2607.28176 · PDF

  7. 07

    Specification-Guided Synthesis of Deadlock-Free Communication Protocol Refinements with Large Language Models

    Yang Li, Ping Hou, Nobuko Yoshida

    cs.SE · cs.AI

    Ensuring behavioural correctness in communication protocols is a central challenge in distributed software systems, as subtle inconsistencies can lead to deadlocks. In such settings, protocol refinement - the safe substitution of a protocol that preserves correctness and compatibility with other components - is essential. Large language models (LLMs) have demonstrated strong capabilities in code generation and program synthesis, yet lack...

    arxiv.org/abs/2607.27964 · 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.