cs.SE · 2026-11-09 · No. 168
Software Engineering, 2026-11-09.
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-
01
When Instruction Files Go Stale: Documentation Debt and Hidden Cost in Coding Agents
Tural Mehtiyev, Biruk Tadesse, Lawrence Arkoh, Wesley Assunção
cs.SE · cs.AI
LLM-based coding agents such as Claude Code are guided by repository instruction files (also called context files or agent configuration files) like AGENTS.md and CLAUDE.md, which are read in every agent session. As any documentation artifact, these files can fall behind the code and become stale (e.g., a test folder moves, but the file still points to the old one). In technical debt terms, such a stale instruction is documentation debt, and...
-
02
TensorMutation: Learning Weight-Space Mutations of Deep Learning Models on Neural Graphs
Zaheed Ahmed, Philip Makedonski, Jens Grabowski
cs.SE · cs.LG
Mutation testing for deep learning (DL) faces a cost-realism trade-off. The pre-training approach produces realistic but computationally expensive mutants, whereas existing post-training operators modify trained models efficiently but produce mutants that less closely resemble real faults. This study asks whether the trade-off is necessary: can the weight-space effect of a fault-informed pre-training mutation operator be predicted from a...
-
03
BOXBOX: Recursive Harness Self-Improvement for Long-Running Performance Optimization
Yuhao Tan, Hanyun Jiang, Fangkai Yang, Yuan Yao, Taolue Chen, Bo Qiao, Yu Kang, Lu Wang, Pu Zhao, Xiaoxing Ma, Qingwei Lin
cs.SE · cs.AI
Automated harness optimization improves agents by learning from trajectories and task feedback. Existing offline methods use reference answers to optimize harnesses for reuse on held-out tasks. However, many real-world tasks are open-ended, while long runs expose new difficulties that offline-optimized harnesses may not address. To study harness optimization in these settings, we introduce PerfRace, a benchmark for long-running performance...
-
04
On the Limits of Execution Traces for Repairing Assertion Failures in LLM-Generated Code
Muntasir Adnan, Carlos C. N. Kuhn
cs.SE · cs.AI
Iterative repair returns a failed program's error to a large language model (LLM) and asks it to fix it. After iterative repair, the remaining failures are mostly assertion failures: with four Qwen2.5 models, they make up 79% of residual failures on BigCodeBench, all on HumanEval and 93% on LiveCodeBench. We argue, through an information view of the feedback, that an assertion failure says little about where the fault lies. We propose...
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.
#D99C5E. Built and served on an always-free VM. The masthead is set 14% letterspaced because newspapers do that and it works.