cs.SE · 2026-10-21 · No. 150
Software Engineering, 2026-10-21.
6 new papers in cs.SE. Titles, authors,
abstracts. Links to arXiv. Want this in your inbox every morning? Subscribe →
01 — The papers
6 entries-
01
ExeBench-FHD: Addressing Fidelity Issues in Decompiler Evaluation
Akarsh Ashok, Dinil Mon Divakaran, Vivek Balachandran
cs.SE · cs.LG · cs.PL
ExeBench is one of the most widely used benchmarks for evaluating LLM-based decompilers. We analyze ExeBench and identify nine issues that affect how faithfully a test measures a decompiler. Three of them prevent LLM decompilers from recovering C code from ExeBench's function. These are ambiguous parameter order when integer and floating-point types are mixed, unused parameters that optimized assembly may drop, and constants stored outside...
-
02
Foreword: Pre-Generation Prediction and Characterisation of LLM Test Failures using the Jacobian Lens
Somin Kim, Robert Feldt, Shin Yoo
cs.SE · cs.LG
Testing LLM-based software is expensive: each input needs several sampled responses, each judged by a costly oracle. Further, every prompt or model change calls for re-testing. Pre-generation adequacy measures cut this cost by ranking inputs by failure risk based on the model's internal state. However, the state of the art, Clotho, models only passing reference inputs, and its hidden-state representation says nothing about why inputs fail. We...
-
03
From Code Generator to Engineering Companion: A Plant-aware Agent for PLC Programming
Joschka Kersting, Gesa Benndorf
cs.SE · cs.AI · cs.LG
Programmable Logic Controller (PLC) coding remains a manual, IDE-centric task that demands constant context switching between documentation, project files, and code editors. Recent work has demonstrated that retrieval-augmented large language models can generate vendor-compliant Structured Text at high compilation rates \cite{pred}, yet these systems treat code generation as a one-shot pipeline: the engineer submits a query and receives code,...
-
04
Hallucinations of Large Language Models in Cross-Language Code Translation: Phenomena and Mitigation
Yali Du, Yunji Zhang, Ming Li
cs.SE · cs.AI
Code translation converts source code from one programming language to another while preserving its functionality. Although Large Language Models (LLMs) have improved code translation, their outputs still contain hallucinations: generated code that conflicts with the source program, violates target-language facts, or introduces contextually inconsistent dependencies. These failures are especially harmful in translation because small semantic...
-
05
From Tokens to Files: Multi-Granularity Detection and Localization of AI-Involved Code
Yue Xu, Xiyang Wang, Hui Liu, Bolei He
cs.SE · cs.CL · cs.LG
The increasing use of large language models for code generation calls for methods that distinguish purely human-written code from AI-involved code: files in which any part, however small, was generated or substantially modified by a model. Beyond flagging such files, we aim to localize the lines or blocks attributable to AI. Existing approaches compress a file into a single score, from surface stylistic features or a global code...
-
06
RAG-NIMBF: A Non-Invasive, Modular Benchmarking Framework for Automated RAG Configuration Analysis
Niclas Hart, Nicolas Weeger
cs.SE · cs.AI
Retrieval-Augmented Generation (RAG) has become the dominant paradigm for grounding the outputs of large language models (LLM) in external knowledge. However, practitioners are faced with a vast configuration space comprising chunking, embedding, retrieval, reranking, prompting and generation models, and there is limited guidance on how these components interact. We present RAG-NIMBF, a modular benchmarking framework that attaches to existing...
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.