CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling Article Swipe

MAKE IMPACT

Zhengyang Tang , Zihan Ye , Chenyu Huang , X. H. Hilda Huang , Chengpeng Li , S. X. Li , GuanHua Chen , Ming Yan , Zizhuo Wang , Hao Zha , Dayiheng Liu , Bo Wang · YOU? · · 2025 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2510.04204

Large Reasoning Models (LRMs) have demonstrated strong capabilities in complex multi-step reasoning, opening new opportunities for automating optimization modeling. However, existing domain adaptation methods, originally designed for earlier instruction-tuned models, often fail to exploit the advanced reasoning patterns of modern LRMs -- In particular, we show that direct fine-tuning on traditional \textit{non-reflective} datasets leads to limited gains. To fully leverage LRMs' inherent reasoning abilities, we propose \textbf{CALM} (\textit{Corrective Adaptation with Lightweight Modification}), a framework that progressively refines LRMs within their native reasoning modes for optimization modeling tasks. In CALM, an expert intervener identifies reasoning flaws and provides concise corrective hints, which the LRM incorporates to produce improved reasoning trajectories. These interventions modify fewer than 2.6\% of generated tokens, but generate high-quality data for soft adaptation through supervised fine-tuning. The adapted model is then further improved through reinforcement learning. Building on CALM, we develop \textbf{STORM} (\textit{Smart Thinking Optimization Reasoning Model}), a 4B-parameter LRM that achieves a new state-of-the-art average accuracy of 68.9\% across five popular optimization modeling benchmarks, matching the performance of a 671B LRM. These results demonstrate that dynamic, hint-based data synthesis both preserves and amplifies the native reasoning patterns of modern LRMs, offering a more effective and scalable path towards expert-level performance on challenging optimization modeling tasks.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2510.04204

PDF

https://arxiv.org/pdf/2510.04204

OA Status

green

OpenAlex ID

https://openalex.org/W4414971175

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4414971175

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2510.04204

Digital Object Identifier

Title

CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2025

Year of publication

Publication date

2025-10-05

Full publication date if available

Authors

Zhengyang Tang, Zihan Ye, Chenyu Huang, X. H. Hilda Huang, Chengpeng Li, S. X. Li, GuanHua Chen, Ming Yan, Zizhuo Wang, Hao Zha, Dayiheng Liu, Bo Wang

List of authors in order

Landing page

https://arxiv.org/abs/2510.04204

Publisher landing page

PDF URL

https://arxiv.org/pdf/2510.04204

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2510.04204

Direct OA link when available

Cited by

0

Total citation count in OpenAlex

Full payload