cs.SE · 2026-11-06 · No. 165

Software Engineering, 2026-11-06.

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

01 — The papers

3 entries
  1. 01

    Accepted but Wrong: Silent Failures of LLM Code Repairs after API Migrations

    Xiaobo Chen, Genliang Zhu, Ziyuan Wang, Chu Wang

    cs.SE · cs.AI

    After a runtime or API migration, an LLM-repaired procedure can run cleanly yet return wrong results, and a release check on typical test inputs ships it. We report a preregistered study of 73 tasks covering 60 documented changes in CPython, Node.js and SQLite. Every candidate is executed on the real runtimes against withheld contracts. Over the complete repair space, the all-assertions gate on typical inputs released 0.410 of wrong repairs....

    arxiv.org/abs/2611.08269 · PDF

  2. 02

    Which Signals of Code Correctness Survive Distribution Shift? Hidden-State and Causal Predictors of Program and Verdict Correctness

    Viola Campos, Thomas Klassert, Adrian Ulges

    cs.SE · cs.LG

    Large language models increasingly judge code, yet without external feedback such judgments are unreliable, and verifying them by executing tests or by extended reasoning is costly. Instead, execution-free correctness predictors use signals from the model's output probabilities, sampled solutions, or hidden states to identify judgments that warrant further verification. However, these predictors may degrade under distribution shifts when...

    arxiv.org/abs/2611.07876 · PDF

  3. 03

    What the Middleman Delivers: Answer Behavior, Tool Permissions, and Billed Usage in LLM API Relays

    Xiaodong Wu, Zhimin Zhao, Qi Li, Chaklam Cheong, Xiangman Li, Jianbing Ni

    cs.SE · cs.AI

    Third-party application programming interface (API) relays offer access to large language models (LLMs), often at lower prices. Users depend on these services for model quality, instruction compliance, and accurate billing. However, existing studies leave unclear whether relays meet these expectations together. We test 20 relays offering GPT-6 Astra and Claude Opus 5. First, we compare answers to knowledge questions with batch-matched...

    arxiv.org/abs/2611.07650 · 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.