VeriSimpl: Robust Optimization Modeling from Natural Language using Simplification-based Verification
Quick Answer
VeriSimpl introduces a robust framework for translating natural language into optimization models, enhancing accuracy through simplification-based verification.
Quick Take
Evaluations demonstrate consistent accuracy improvements over existing methods, providing a high-precision self-verification signal across various optimization benchmarks.
Key Points
- VeriSimpl leverages simplification-based verification for optimization modeling.
- The framework improves accuracy over existing natural language processing methods.
- It generates simplified diagnostic queries for better reasoning about formulations.
- Evaluations show consistent performance improvements across various benchmarks.
- The approach offers a novel self-verification signal for optimization tasks.
Paper Resources
📖 Reader Mode
~2 min readAbstract:Natural language interfaces can greatly benefit the accessibility and usability of optimization modeling, and recent advances in large language models (LLMs) show promise in automatically translating textual problem descriptions into executable solver formulations. However, a key challenge for existing approaches is to ensure that the inferred formulation correctly implements the intended task, even if it may execute without errors. We introduce VeriSimpl, a solver LLM framework for robust natural-language-to-optimization formalization. Our approach is based on the idea of simplification-based verification, where the optimization solver is leveraged to generate simplified diagnostic queries about a candidate formulation to allow the LLM to tractably reason about the correctness of the formulation with respect to the task description. We present such simplification strategies along different dimensions with respect to problem constraints and decision variables, which allow the LLM to reason locally under fixed global contexts. Evaluations on a range of optimization benchmarks show how our approach provides consistent improvements in accuracy over existing methods, while also providing a novel high-precision self-verification signal.
| Comments: | ICML 2026 |
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2607.20474 [cs.AI] |
| (or arXiv:2607.20474v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2607.20474 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Sumaya Abdul Rahman [view email]
[v1]
Sun, 24 May 2026 13:46:54 UTC (2,009 KB)
— Originally published at arxiv.org
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.