cs.SE · 2026-10-28 · No. 156

Software Engineering, 2026-10-28.

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

    FeatureArc: Benchmarking Coding Agents on Evolving Features

    Yunlong Wang, Alyssa Wu, Cuiyun Gao, Jia Feng, Songyuanyi Lu, Zhichao Hu

    cs.SE · cs.AI

    A software feature usually evolves over time: developers extend its first version as new use cases and requirements arrive, and each extension builds on code written earlier. Most feature benchmarks evaluate a single request on a fixed codebase. Feature evolution requires evaluating successive extensions on an agent's own earlier code and checking whether the feature remains correct. We introduce FeatureArc to evaluate coding agents on...

    arxiv.org/abs/2610.37434 · PDF

  2. 02

    Spine: Compiling Subtask Trees into Structured Context for Long-Horizon Coding Agents

    Jiahong Xiang, Kunqiu Chen, Lingming Zhang, Yuqun Zhang

    cs.SE · cs.AI

    Long-horizon coding tasks contain nested subtasks. Typically, agents record interactions sequentially into a growing history, causing context inflation and performance degradation. Compressing or trimming the history without explicit subtask boundaries can discard information needed by unfinished subtasks. Conversely, recursive subagent delegation isolates completed subtasks through child agents by assigning every subtask boundary to...

    arxiv.org/abs/2610.37224 · PDF

  3. 03

    Beyond QASecClaw: Agent Scaling, Verifier Feedback, and Evidence Reliability in Software Assurance

    S M Abdulla Al Mamun, Akif Islam, Mohd. Ruhul Ameen

    cs.SE · cs.AI

    Can additional specialist language-model contexts improve software assurance when deterministic tool evidence is already available? We study this question through five experiments spanning authored Java warning controls, OWASP Benchmark assessment, Defects4J test generation, SV-COMP assertion verdicts, and deliberately misleading evidence packages. The evaluated systems use Qwen2.5-Coder-7B-Instruct, with a 1.5B sensitivity analysis, and...

    arxiv.org/abs/2610.36947 · 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.