cs.SE · 2026-07-10 · No. 49

Software Engineering, 2026-07-10.

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

    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

  2. 02

    TTHE: Test-Time Harness Evolution

    Jun Nie, Yonggang Zhang, Jun Song, Qianshu Cai, Dahai Yu, Yike Guo, Xinmei Tian, Bo Han

    cs.SE · cs.LG

    The behavior of an LLM agent is determined not only by the underlying model, but also by its harness: the executable program that constructs context, invokes tools, verifies intermediate results, and recovers from failures. Existing approaches optimize such harnesses before deployment, searching training or development data for a fixed agent workflow that is then frozen at test time. This limits adaptation when the test distribution, failure...

    arxiv.org/abs/2607.08124 · PDF

  3. 03

    Aleena: Alignment Agent for Research Software Engineering Collaborations

    Kshitij Dani, Cordero Core, Landung Setiawan, Carlos Garcia Jurado Suarez, Anshul Tambay, Vani Mandava, Anant Mittal

    cs.SE · cs.AI

    Research software collaborations span meetings, informal chats, pull requests, and GitHub issues. A decision surfaced in a Slack thread, refined in a meeting, and implemented in a pull request can lose its original rationale across these artifacts, leaving domain researchers and research software engineers with divergent mental models of project intent, ownership, and scientific assumptions. We argue that alignment in research software...

    arxiv.org/abs/2607.08043 · PDF

  4. 04

    3100 Opinions on Code Review in an AI World: Building Causal Theory from Practitioner Discourse

    Shyam Agarwal, Courtney Miller, Christian Kästner, Bogdan Vasilescu

    cs.SE · cs.AI

    Coding agents now author entire pull requests, and practitioners sharply disagree about what this does to code review: whether it becomes the bottleneck, whether human review is still necessary, and whether it quietly erodes the understanding that it once built. Repository-mining studies measure surface trends but seldom explain the mechanisms beneath them, and the trends themselves prove unstable. A motivating observational analysis of...

    arxiv.org/abs/2607.07980 · 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.