大模型
arxiv.org ·
SLMFix：利用小型语言模型通过强化学习修复领域特定语言错误
该论文提出 SLMFix，一种代码生成流水线：用强化学习微调小型语言模型，依据解释器反馈修复 LLM 为领域特定语言（DSL）生成的程序中的语法错误。实验显示，在低资源编程语言上验证器通过率提升 40%，在高资源 DSL 上消除超过 50% 的语法错误；在 Ansible、Lean 等低资源语言上，该方法对基座模型提升显著，并优于监督微调方案（含 7B 模型）。作者为 David Jiahao Fu、Aryan Gupta、Aaron Councilman、Yu-Xiong Wang、Vikram Adve，v1 于 2025 年 11 月 24 日提交，v2 于 2026 年 9 月 25 日修订。
AI推荐理由 arXiv 论文（cs.SE/cs.AI/cs.PL），作者来自 UIUC 团队（Vikram Adve、Yu-Xiong Wang 等），摘要给出具体实验结论：在低资源编程语言上验证器通过率提升 40%，高资源 DSL 消除超过 50% 语法错误，并在 Ansible、Lean 上优于监督微调。新信息是用强化学习微调小模型、基于解释器反馈修复 LLM 生成 DSL 程序的语法错误，对代码生成与 Agent 工具链有实际参考价值。局限是仅有摘要，缺少数据集规模、基线细节与复现信息，效果需以论文正文为准。
78
正文
Computer Science > Software Engineering
arXiv:2511.19422 (cs)
[Submitted on 24 Nov 2025 (v1), last revised 25 Sep 2026 (this version, v2)]
Title:SLMFix: Leveraging Small Language Models for Domain Specific Language Error Fixing with Reinforcement Learning
Authors:David Jiahao Fu, Aryan Gupta, Aaron Councilman, Yu-Xiong Wang, Vikram Adve
View a PDF of the paper titled SLMFix: Leveraging Small Language Models for Domain Specific Language Error Fixing with Reinforcement Learning, by David Jiahao Fu and 4 other authors
View PDF
HTML (experimental)
Abstract:Large language models (LLMs) have shown impressive capabilities in code generation across many programming languages but even state-of-the-art LLMs generate programs that contain syntactic errors and fail to complete the given tasks, especially for low-resource programming languages (LRPLs). In addition, the high cost of training makes finetuning LLMs unaffordable for those with constrained computational resources, further weakening the effectiveness of LLMs for code generation. In this work, we propose SLMFix, a novel code generation pipeline that leverages a small language model (SLM) finetuned using reinforcement learning (RL) techniques to fix syntactic errors in LLM-generated programs for domain-specific languages (DSLs) based on interpreter feedback. Our experimental results demonstrate the effectiveness and generalizability of our approach across multiple DSLs, improving the validator pass rates by 40% on LRPLs and eliminating more than 50% of syntactic errors for high-resource DSLs. Notably, SLMFix brings substantial performance improvement to the base model and outperforms supervised finetuning approach even for 7B models on LRPLs including Ansible and Lean, showing the potential of our approach in improving the quality of LLM-generated programs.
Subjects:
Software Engineering (cs.SE); Artificial Intelligence (cs.AI); Programming Languages (cs.PL)
Cite as:
arXiv:2511.19422 [cs.SE]
(or
arXiv:2511.19422v2 [cs.SE] for this version)
https://doi.org/10.48550/arXiv.2511.19422
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: David Jiahao Fu [view email]
[v1]
Mon, 24 Nov 2025 18:56:47 UTC (479 KB)
[v2]
Fri, 25 Sep 2026 17:41:38 UTC (478 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled SLMFix: Leveraging Small Language Models for Domain Specific Language Error Fixing with Reinforcement Learning, by David Jiahao Fu and 4 other authors
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.SE
new
|
recent
| 2025-11
Change to browse by:
cs
cs.AI
cs.PL
References & Citations
NASA ADS
Google Scholar
Semantic Scholar
export BibTeX citation
Loading...
BibTeX formatted citation
×
loading...
Data provided by:
Bookmark
Bibliographic Tools
Bibliographic and Citation Tools
Bibliographic Explorer Toggle
Bibliographic Explorer (What is the Explorer?)
Connected Papers Toggle
Connected Papers (What is Connected Papers?)
Litmaps Toggle
Litmaps (What is Litmaps?)
scite.ai Toggle
scite Smart Citations (What are Smart Citations?)
Code, Data, Media
Code, Data and Media Associated with this Article
alphaXiv Toggle
alphaXiv (What is alphaXiv?)
Links to Code Toggle
CatalyzeX Code Finder for Papers (What is CatalyzeX?)
DagsHub Toggle
DagsHub (What is DagsHub?)
GotitPub Toggle
Gotit.pub (What is GotitPub?)
Huggingface Toggle
Hugging Face (What is Huggingface?)
ScienceCast Toggle
ScienceCast (What is ScienceCast?)
Demos
Demos
Replicate Toggle
Replicate (What is Replicate?)
Spaces Toggle
Hugging Face Spaces (What is Spaces?)
Spaces Toggle
TXYZ.AI (What is TXYZ.AI?)
Related Papers
Recommenders and Search Tools
Link to Influence Flower
Influence Flower (What are Influence Flowers?)
Core recommender toggle
CORE Recommender (What is CORE?)
Author
Venue
Institution
Topic
About arXivLabs
arXivLabs: experimental projects with community collaborators
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Which authors of this paper are endorsers? |
Disable MathJax (What is MathJax?)