cs.SE · 2026-08-21 · No. 91

Software Engineering, 2026-08-21.

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

    From Agent Behaviour to Agent-Friendly Documentation: An Empirical Study of How Coding Agents Discover, Read, and Write Technical Documentation

    Zhijun Gao, Jing Chen

    cs.SE · cs.AI · cs.HC

    Technical documentation is written for human developers, but an increasing share of software changes is now authored by autonomous coding agents. Which documents they consult, when, and what follows remain unknown. We conduct a behaviour-grounded study of agent-documentation interaction across two public datasets: 557 agentic coding sessions from SWE-chat, yielding 94,813 development events including 3,033 documentation interactions; and...

    arxiv.org/abs/2608.20195 · PDF

  2. 02

    Repo0: Design-Driven Zero-to-All Code Generation

    Silin Chen, Haoyi Teng, Xiaodong Gu, Yuling Shi, Jiale Huang, Yongpan Wang, Hongyu Zhang, Haibing Guan

    cs.SE · cs.AI

    Large language model agents have made substantial progress in code generation, yet most existing systems assume a predefined repository architecture. This assumption does not hold in zero-to-all code generation, where an agent must construct an entire software project directly from natural-language requirements while maintaining a modular repository architecture throughout development. We present Repo0, a continuous structural evolution...

    arxiv.org/abs/2608.19854 · PDF

  3. 03

    Loreley: Repository-Scale Program Evolution with Quality-Diversity Search

    Mohan Chen

    cs.SE · cs.AI

    Sequential agent search accumulates changes from its current champion but discards alternative branches; independent proposals preserve breadth but restart from the root. Loreley instead retains complete repository states in a Quality-Diversity (QD) archive and samples them as parents or supplies them as context for later edits. Candidates are Git commits produced in isolated worktrees and judged by a project-supplied evaluator. We compare...

    arxiv.org/abs/2608.19703 · PDF

  4. 04

    Accelerated Genetic Programming Hyper-Heuristics for Simulation-Based Scheduling via Agentic AI

    Heyang Thomas Li, Alexander Pletzer, Yuan Tian, Yi Mei, Mengjie Zhang

    cs.SE · cs.AI · cs.NE

    Python is widely used in scientific research because it enables rapid development and provides rich ecosystems for data analysis, artificial intelligence (AI), and machine learning. However, customized research code can become prohibitively slow as experiments scale. This challenge is particularly acute in discrete-event project-scheduling simulations, where sequential state updates, nested loops, conditional evaluations, and object-oriented...

    arxiv.org/abs/2608.19487 · PDF

  5. 05

    Measuring What a Specification Determines: A Formal Semantic-Block Model and an Execution-Judged Benchmark

    Oleg Grynets, Dmytro Kostetskyi, Vasyl Lyashkevych

    cs.SE · cs.AI · cs.CL · cs.LO

    This work introduces a formal semantic-block model for specifications and an execution-judged benchmark for evaluating specification quality independently of model capability. A specification is represented as a structure comprising semantic blocks, dependency relations, block-owned rules, decision points, and explicitly open questions, subject to four machine-checkable well-formedness conditions: acyclicity, single ownership, constraint...

    arxiv.org/abs/2608.19475 · 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.