AI Paper Atlas

Research map / Large language models / Instruction and fine-tuning

CALM Before the STORM: Unlocking Native Reasoning for Optimization Modeling

Zhengyang Tang, Zihan Ye, Chenyu Huang, Xuhan Huang, Chengpeng Li, Sihang Li, Guanhua Chen, Ming Yan, Zizhuo Wang, Hongyuan Zha, Dayiheng Liu, Benyou Wang

ICML 2026 · Large language models › Instruction and fine-tuning · approach: Fine-tuning for reasoning data · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
fine-tune on OR-Instruct-3K full solutions (ablation)Qwen3-4B-Thinking-2507 · NL4Optpass@1: 85.8 -> 92.9Improved
fine-tune on OR-Instruct-3K full solutions (ablation)Qwen3-4B-Thinking-2507 · OptMathpass@1: 33.1 -> 6.6Hurt
fine-tune on OR-Instruct-3K full solutions (ablation)Qwen3-4B-Thinking-2507 · IndustryORpass@1: 46.2 -> 27.5Hurt
fine-tune on OR-Instruct-3K full solutions (ablation)Qwen3-4B-Thinking-2507 · 5-benchmark macro averagepass@1: 57.1 -> 51.2Hurt
SFT on CALM-corrected solutions instead of OR-Instruct-3K (ablation)Qwen3-4B-Thinking-2507 · MAMO Complexpass@1: 40.5 -> 54.3 (base 46.5)Improved
SFT on CALM-corrected solutions (ablation)Qwen3-4B-Thinking-2507 · 5-benchmark macro averagepass@1: 57.1 -> 58.7Improved
SFT on CALM-corrected solutions (ablation)Qwen3-4B-Thinking-2507 · IndustryOR and OptMathpass@1: 46.2 -> 44.1; 33.1 -> 30.4No clear effect
add RL (GRPO) after CALM-SFT (ablation)CALM-SFT model · 5-benchmark macro averagepass@1: 58.7 -> 68.9Improved
CALM local correction vs DeepSeek-R1 full-solution distillation before RL (ablation)STORM pipeline · Hard-3 AVG (matched control)pass@1: 47.4 -> 54.9Improved
CALM local correction vs Gemini-2.5-Pro full-solution distillation before RL (ablation)STORM pipeline · Hard-3 AVG (matched control)pass@1: 30.8 -> 54.9Improved
DeepSeek-R1 distillation vs CALM on IndustryOR (ablation)STORM pipeline · IndustryOR (matched control)pass@1: 50.4 vs 50.0No clear effect
swap Gemini-2.5-Pro intervener for open-source DeepSeek-R1-0528 (ablation)CALM · 5-benchmark macro averagepass@1: 68.9 -> 67.8No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy