arXiv cs.CL· Amer Goel, Yeganeh Alimohammadi, Andrew Daw·· 12 小时前AI 评分31
ASTOR：用形式化语法为软约束优化建模并评测自动形式化
ASTOR: Benchmarking and Improving Autoformulation for Soft-Constraint Optimization with a Formal Grammar
AI 导读
ASTOR 是一个推理时框架，先将自然语言决策问题映射为语法引导的抽象语法树（AST），再确定性地编译为可执行的优化代码。团队同时发布聚焦软约束建模的统一基准 SoftOR，ASTOR 在该基准上取得同类单次请求与多智能体 LLM 方法中最佳的综合准确率，并在仅含硬约束的标准自动形式化基准上保持竞争力。代码与数据已公开。
正文 · 原文
Abstract:Real-world decision problems combine two qualitatively different kinds of constraints: requirements that must be satisfied, called hard constraints, and preferences that can be violated, called soft constraints. Because these problems are often posed to decision-makers in natural language, large language models offer a natural tool for assisting with their solution. This has given rise to autoformulation, which focuses on using LLMs to translate natural-language descriptions of decision problems into executable mathematical optimization models. However, this research often neglects soft constraints like those proposed by consumers, managers, and planners, despite the fact that many practical problems require modeling them explicitly. We introduce ASTOR, an inference-time framework that maps a natural-language decision problem to a grammar-guided abstract syntax tree (AST) before deterministically compiling the resulting representation into executable optimization code. We also introduce SoftOR, a unified benchmark of natural language problems which focuses on soft constraint formulations. On SoftOR, ASTOR achieves the best aggregate accuracy among comparable single-request and multi-agent LLM methods while remaining competitive on standard autoformulation benchmarks that include only hard constraints. Code and data are available at this https URL.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.26819 [cs.CL] |
| (or arXiv:2610.26819v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.26819 arXiv-issued DOI via DataCite |
Submission history
From: Amer Goel [view email]
[v1]
Mon, 19 Oct 2026 17:52:35 UTC (880 KB)
[v2]
Thu, 22 Oct 2026 18:21:47 UTC (882 KB)
来源：arXiv cs.CL · arxiv.org