智能体
arxiv.org ·
用 LLM 智能体改进约束模型
论文提出一种智能体框架，让 LLM 智能体在 CPMpy 建模库中从开放式空间重写约束模型：给定一个模型和三个训练实例，智能体提出替代形式，把解注入原模型进行经验验证，并诊断修复失败，中位约 15 分钟返回最佳变体。在 9 个组合优化问题的 27 个测试实例上，生成模型在 21 个实例上优于原始模型，部分问题求解快两个数量级以上；与复用相同验证与选择工具的非智能体基线对比显示，增益来自智能体的迭代诊断与修复，而非仅采样多个候选。
AI推荐理由 arXiv 论文（v2，2026-09-22 修订），作者为 Florentina Voboril 与 Stefan Szeider，摘要给出可核验的实验设置：LLM 智能体在 CPMpy 中重写约束模型，用三个训练实例提出候选、将解注入原模型做经验验证并诊断修复，中位约 15 分钟返回最佳变体；在 9 个组合优化问题的 27 个测试实例中 21 个优于原始模型，部分问题求解快两个数量级以上，且与非智能体基线对比表明增益来自迭代诊断修复而非单纯采样。局限是仅在 CPMpy 与 9 个问题上验证，正确性依赖经验验证而非构造性证明。
78
正文
Computer Science > Artificial Intelligence
arXiv:2608.08127 (cs)
[Submitted on 8 Aug 2026 (v1), last revised 22 Sep 2026 (this version, v2)]
Title:Improving Constraint Models with LLM Agents
Authors:Florentina Voboril, Stefan Szeider
View a PDF of the paper titled Improving Constraint Models with LLM Agents, by Florentina Voboril and Stefan Szeider
View PDF
HTML (experimental)
Abstract:The runtime of Constraint Programming (CP) solvers is highly sensitive to modeling choices, such as symmetry breaking, implied constraints, global constraints, constraint reformulation, and variable representation. Improving these constraint models has traditionally required human expertise, and existing automated reformulation systems are restricted to a predefined library of hand-crafted transformation rules. We introduce an agentic framework that instead reformulates a constraint model from an open-ended space and establishes correctness empirically rather than by construction: a Large Language Model (LLM) agent, given a model and three training instances, proposes alternative formulations, validates each by injecting its solution back into the original model, and diagnoses and repairs failures, returning the best variant it finds in a median of about fifteen minutes. The models are expressed in the CPMpy modeling library, and each proposed model is evaluated on three larger test instances. Across nine combinatorial optimization problems, the generated models outperform the originals on 21 of 27 test instances, and on some problems solve more than two orders of magnitude faster. A comparison against non-agentic baselines that reuse the same validation and selection tools indicates that the gains stem from the agent's iterative diagnosis and repair, not merely from sampling several candidates. These results demonstrate that autonomous agentic methods can support the improvement of constraint models.
Subjects:
Artificial Intelligence (cs.AI); Logic in Computer Science (cs.LO); Software Engineering (cs.SE)
Cite as:
arXiv:2608.08127 [cs.AI]
(or
arXiv:2608.08127v2 [cs.AI] for this version)
https://doi.org/10.48550/arXiv.2608.08127
Focus to learn more
arXiv-issued DOI via DataCite
Submission history
From: Stefan Szeider [view email]
[v1]
Sat, 8 Aug 2026 13:22:30 UTC (49 KB)
[v2]
Tue, 22 Sep 2026 09:31:55 UTC (36 KB)
Full-text links:
Access Paper:
View a PDF of the paper titled Improving Constraint Models with LLM Agents, by Florentina Voboril and Stefan Szeider
View PDF
HTML (experimental)
TeX Source
view license
Current browse context:
cs.AI
new
|
recent
| 2026-08
Change to browse by:
cs
cs.LO
cs.SE
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?)