AI Paper Atlas

Research map / Large language models / Agents, code and math

Opt-Verifier: Unleashing the Power of LLMs for Optimization Modeling via Dual-Side Verification

Haoyang Liu, Jie Wang, Boxuan Niu, Xiongwei Han, Yian Xu, Mingxuan Ye, Zijie Geng, Fangzhou Zhu, Tao Zhong, Mingxuan Yuan, Jianye HAO

ICML 2026 · Large language models › Agents, code and math · approach: LLMs for optimization and heuristics · 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
add structure-augmented modeling (ablation)Opt-Verifier · Mamo ComplexLPsolving accuracy: 54.2 -> 66.7Improved
add structure-augmented modeling (ablation)Opt-Verifier · ComplexORsolving accuracy: 63.1 -> 78.9Improved
add structure-side verification (ablation)Opt-Verifier · IndustryORsolving accuracy: 29.0 -> 45.0Improved
add solution-side verification (ablation)Opt-Verifier · IndustryORsolving accuracy: 41.0 -> 45.0Improved
add solution-side verification (ablation)Opt-Verifier · ComplexORsolving accuracy: 68.4 -> 78.9Improved
add high-level structure (ablation)Opt-Verifier · ComplexORsolving accuracy: 78.9 -> 78.9No clear effect
add high-level structure (ablation)Opt-Verifier · Mamo ComplexLPsolving accuracy: 59.9 -> 66.7Improved
add low-level structure (ablation)Opt-Verifier · IndustryORsolving accuracy: 30.0 -> 45.0Improved
add medium-level structure (ablation)Opt-Verifier · IndustryORsolving accuracy: 38.0 -> 45.0Improved
add Opt-Verifier on top of ORLMORLM · Mamo ComplexLPsolving accuracy: 38.8 -> 59.6Improved
add Opt-Verifier on top of OptiMUSOptiMUS · NL4Optsolving accuracy: 83.0 -> 96.1Improved
add Opt-Verifier to GPT-4o backboneGPT-4o · NL4Optsolving accuracy: 79.4 -> 97.5Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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