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
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add structure-augmented modeling (ablation) | Opt-Verifier · Mamo ComplexLP | solving accuracy: 54.2 -> 66.7 | Improved |
| add structure-augmented modeling (ablation) | Opt-Verifier · ComplexOR | solving accuracy: 63.1 -> 78.9 | Improved |
| add structure-side verification (ablation) | Opt-Verifier · IndustryOR | solving accuracy: 29.0 -> 45.0 | Improved |
| add solution-side verification (ablation) | Opt-Verifier · IndustryOR | solving accuracy: 41.0 -> 45.0 | Improved |
| add solution-side verification (ablation) | Opt-Verifier · ComplexOR | solving accuracy: 68.4 -> 78.9 | Improved |
| add high-level structure (ablation) | Opt-Verifier · ComplexOR | solving accuracy: 78.9 -> 78.9 | No clear effect |
| add high-level structure (ablation) | Opt-Verifier · Mamo ComplexLP | solving accuracy: 59.9 -> 66.7 | Improved |
| add low-level structure (ablation) | Opt-Verifier · IndustryOR | solving accuracy: 30.0 -> 45.0 | Improved |
| add medium-level structure (ablation) | Opt-Verifier · IndustryOR | solving accuracy: 38.0 -> 45.0 | Improved |
| add Opt-Verifier on top of ORLM | ORLM · Mamo ComplexLP | solving accuracy: 38.8 -> 59.6 | Improved |
| add Opt-Verifier on top of OptiMUS | OptiMUS · NL4Opt | solving accuracy: 83.0 -> 96.1 | Improved |
| add Opt-Verifier to GPT-4o backbone | GPT-4o · NL4Opt | solving accuracy: 79.4 -> 97.5 | Improved |
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.
- OptiMUS — OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models (ICML 2024) · better on 6 of 6 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
- OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling (ICLR 2025 · similarity 0.89)
- OptiTree: Hierarchical Thoughts Generation with Tree Search for LLM Optimization Modeling (NeurIPS 2025 · similarity 0.87)
- MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling (NeurIPS 2026 · similarity 0.87)
- LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch (ICLR 2025 · similarity 0.86)
- Step-by-Step Optimization-like Reasoning in LLMs over Expanding Search Spaces (NeurIPS 2026 · similarity 0.86)
- Autoformulation of Mathematical Optimization Models Using LLMs (ICML 2025 · similarity 0.86)
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.
