Can Language Models Go beyond Coding? Assessing the Capability of Language Models to Build Real-World Systems
ACM Transactions on Software Engineering and Methodology · 30.11.2026 · 35 (11) · 1-39
DOI: 10.1145/3816153 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Software Engineering and Methodology, online erschienen am 04.11.2026. Verfasst von Chenyu Zhao und 10 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref) und nennt 82 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Fundamental Research Funds for the Central Universities.
Abstract (Originalsprache)
Large language models (LLMs) have shown growing potential in software engineering, yet few benchmarks evaluate their ability to repair software during migration across instruction set architectures (ISAs). Cross-ISA migration, such as between x86_64 and aarch64 , requires handling complex dependencies, heterogeneous toolchains, and long build logs while ensuring executable verification. To address this challenge, we present Build-bench (Homepage: https://aiops-lab-nku.github.io/Build-bench/ , Code at https://github.com/zcyyc/Build-bench ), an end-to-end benchmark that systematically evaluates the capability of LLMs to repair build failures in cross-ISA settings. Build-bench collects 268 real-world failed packages and integrates auxiliary tools including Structure Extraction , File Content Extraction , Content Modification , and Build Verification to support autonomous, tool-augmented reasoning. The repair process operates in an iterative loop where, upon failure, the model receives updated build logs and previous repair outcomes to refine subsequent attempts. Through a comparative evaluation across the studied models, Build-bench reveals that current models achieve a maximum build success rate of 63.19% and tool usage patterns differ significantly across models. By coupling real build environments with verifiable outcomes, Build-bench establishes the first architecture-aware benchmark for studying LLM-based software build and repair.
Förderung
- National Natural Science Foundation of China
- Fundamental Research Funds for the Central Universities
Zitieren
APA
Zhao, C., Zhang, S., Huang, Z., Jin, W., Sun, Y., Pei, D., Zhang, C., Lin, Q., Bansal, C., Rajmohan, S., & Ma, M. (2026). Can Language Models Go beyond Coding? Assessing the Capability of Language Models to Build Real-World Systems. ACM Transactions on Software Engineering and Methodology, 35(11), 1-39. https://doi.org/10.1145/3816153
Vancouver
Zhao C, Zhang S, Huang Z, Jin W, Sun Y, Pei D, et al. Can Language Models Go beyond Coding? Assessing the Capability of Language Models to Build Real-World Systems. ACM Transactions on Software Engineering and Methodology. 2026;35(11):1-39. doi:10.1145/3816153
BibTeX
@article{Zhao2026,
author = {Zhao, Chenyu and Zhang, Shenglin and Huang, Zeshun and Jin, Weilin and Sun, Yongqian and Pei, Dan and Zhang, Chaoyun and Lin, Qingwei and Bansal, Chetan and Rajmohan, Saravan and Ma, Minghua},
title = {Can Language Models Go beyond Coding? Assessing the Capability of Language Models to Build Real-World Systems},
journal = {ACM Transactions on Software Engineering and Methodology},
year = {2026},
volume = {35},
number = {11},
pages = {1--39},
doi = {10.1145/3816153}
}
EUVIMED