cs.SE · 2026-08-06 · No. 76

Software Engineering, 2026-08-06.

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

01 — The papers

10 entries
  1. 01

    RepairFormer: Automated Repair of Structured Inputs Using Transformers

    Ovi Paul, Tom J King, Ali Shokri

    cs.SE · cs.AI

    Structured input files such as JSON, DOT, OBJ, INI, S-expression, and TinyC are widely used in software systems, but small corruptions can cause parsers to reject otherwise useful data. Repairing such inputs is important because malformed configuration, program, and data files can interrupt testing, analysis, deployment, and downstream automation even when most of the original content remains intact. Existing repair techniques can produce...

    arxiv.org/abs/2608.05060 · PDF

  2. 02

    SciCode-Verified: How Benchmark Defects Underestimated the Scientific-Coding Ability of Language Models

    Sihan Hu, Lyuhan Huang, Youjin Deng, Kun Chen

    cs.SE · cs.AI

    SciCode is the standard measure of the scientific-coding ability of language models: research-level problems that demand both frontier scientific theory and its implementation as working numerical code. It is a component of the Artificial Analysis Intelligence Index and a standing evaluation in government and national-laboratory suites. Yet its scores have recently plateaued: the strongest 2026 models cluster tightly around 60\% subproblem...

    arxiv.org/abs/2608.04975 · PDF

  3. 03

    A Chain Is Only as Strong as Its Weakest Link: A Scoping Review of System Integration Audits in AI

    Leah Davis, Dominic Martin, AJung Moon

    cs.SE · cs.AI

    As AI systems become increasingly integrated into diverse interfaces and applications, model-centric audits are insufficient to address risks arising from interactions among system components and deployment environments. System integration has long been central to software audits in safety-critical domains such as aerospace. However, its role in AI auditing remains underexplored. Scanning through 4,259 documents, we present a scoping review...

    arxiv.org/abs/2608.04921 · PDF

  4. 04

    Scrouting: Cost-Aware Routing of Coding Agents by Scouting the Repository First

    Ishaan Bhola, Adithyan Krishnan, Mukunda NS

    cs.SE · cs.AI

    Frontier language models can resolve repository-level software issues, but each attempt is expensive, and existing routers select a model from the issue text alone. We present SuperScout, which routes after scouting the repository: a 7B searcher, SuperScout-7B, first explores the repository and produces a structured handoff whose reproduction claims are sandbox-verified, with false claims stripped before delivery. The searcher's hidden...

    arxiv.org/abs/2608.04804 · PDF

  5. 05

    RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists

    Yuexi Yang, Alyssa Wu, Ji Luo, Richeng Xuan, Zhichao Hu, Yuhong Liu, Zhen Qin

    cs.SE · cs.AI

    The integration of Large Language Models (LLMs) into software engineering has shifted the focus from function-level generation to repository-scale assistance. However, existing benchmarks largely rely on bug reports from GitHub Issues, which often allow models to bypass genuine understanding via pattern matching on error logs. This misalignment under-measures Edit Bias, which refers to premature generation, where models prematurely propose...

    arxiv.org/abs/2608.04783 · PDF

  6. 06

    What We Observe as LLM Behavior Can Be a Side-effect of Inference Backend

    Shahed Masoudian, Passant Shafaei, Monorama Swain, Markus Schedl

    cs.SE · cs.AI · cs.LG

    Benchmark scores are reported as properties of a model, yet the inference framework used to produce them, such as HuggingFace, vLLM, or Ollama, are considered non-influential and their names and versions are almost never disclosed. In this work we investigate how much this choice can influence the model output. In a fully-crossed study (three instruction-tuned models x five inference frameworks x six benchmarks x four generation modes) we...

    arxiv.org/abs/2608.04714 · PDF

  7. 07

    Active-SWE: Benchmarking Coding Agents for Proactive Bug Fixing without Issue Reports

    Haobin Li, Ping Deng, Weizhong Qian, Liang Jiang, Zhenyu Huang, Mouxing Yang, Xi Peng

    cs.SE · cs.AI

    Coding agents powered by large language models (LLMs) are increasingly adopted in software engineering (SWE) scenarios, capable of fixing a specific bug in large-scale codebase. However, existing SWE benchmarks typically assume that high-quality issue reports with detailed information are always available, which is easily violated in practice due to the complexity of report acquisition and curation. To address this, we introduce Active-SWE, a...

    arxiv.org/abs/2608.04682 · PDF

  8. 08

    The Order Is the Guarantee: Verifier-Budgeted Code Deletion with Static-First Learned Proposals

    Ruitong Li, Binjie Guo, Aisheng Mo, Guowei Su, Han Wang, Jie Li, Ru Zhang

    cs.SE · cs.AI

    Frontier coding models now match or exceed strong human reference points on programming benchmarks, yet benchmark success does not imply maintainable software. Prompt-driven "vibe coding" is additive: new branches, guards, and fallbacks accumulate faster than obsolete logic is removed. We study the inverse problem-how an Al system should remove code when execution-verification capacity is finite. We formulate redundant-code reduction as...

    arxiv.org/abs/2608.04611 · PDF

  9. 09

    ExeCRE: Execution-Consistency Guided Reliability Estimation for Self-Correcting Code Generation

    Yiru Dong, Richong Zhang, Fanshuang Kong, Si Chen

    cs.SE · cs.AI

    Large language models (LLMs) have made notable progress in code generation, but they still struggle on challenging tasks that require sophisticated algorithms or complex implementations. Recent methods increasingly use code execution as feedback, especially in self-correction pipelines that construct verification signals from generated code. However, these pipelines often depend on supervision signals whose reliability is unknown, which can...

    arxiv.org/abs/2608.04439 · PDF

  10. 10

    COMPAS: Difficulty-Aware Joint Search for Optimizing Code Generation

    Jingzhi Gong, Jie M. Zhang, Gunel Jahangirova, Dong Huang, Mohammad Reza Mousavi, Mark Harman

    cs.SE · cs.AI

    Code generation systems make each LLM call with a model, a prompt, and decoding settings. However, existing optimization methods usually tune only part of these choices or use one fixed configuration for all tasks: global optimizers search one configuration for all tasks, routers choose only a model, and prompt optimizers keep the model and decoding settings fixed. This leaves their joint, group-specific interactions unclear. We therefore...

    arxiv.org/abs/2608.04336 · 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.