OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866918464370769920 |
|---|---|
| author | Zhang, Xinyu Zhang, Boxuan Wan, Yuchen Zhang, Lingling Yao, YiXing Wei, Bifan Wu, Yaqiang Liu, Jun |
| author_facet | Zhang, Xinyu Zhang, Boxuan Wan, Yuchen Zhang, Lingling Yao, YiXing Wei, Bifan Wu, Yaqiang Liu, Jun |
| contents | While Large Language Models (LLMs) demonstrate remarkable reasoning, complex optimization tasks remain challenging, requiring domain knowledge and robust implementation. However, existing benchmarks focus narrowly on Mathematical Programming and Combinatorial Optimization, hindering comprehensive evaluation. To address this, we introduce OptiVerse, a comprehensive benchmark of 1,000 curated problems spanning neglected domains, including Stochastic Optimization, Dynamic Optimization, Game Optimization, and Optimal Control, across three difficulty levels: Easy, Medium, and Hard. The experiments with 22 LLMs of different sizes reveal sharp performance degradation on hard problems, where even advanced models like GPT-5.2 and Gemini-3 struggle to exceed 27% accuracy. Through error analysis, we identify that modeling & logic errors remain the primary bottleneck. Consequently, we propose a Dual-View Auditor Agent that improves the accuracy of the LLM modeling process without introducing significant time overhead. OptiVerse will serve as a foundational platform for advancing LLMs in solving complex optimization challenges. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_21510 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving Zhang, Xinyu Zhang, Boxuan Wan, Yuchen Zhang, Lingling Yao, YiXing Wei, Bifan Wu, Yaqiang Liu, Jun Computation and Language While Large Language Models (LLMs) demonstrate remarkable reasoning, complex optimization tasks remain challenging, requiring domain knowledge and robust implementation. However, existing benchmarks focus narrowly on Mathematical Programming and Combinatorial Optimization, hindering comprehensive evaluation. To address this, we introduce OptiVerse, a comprehensive benchmark of 1,000 curated problems spanning neglected domains, including Stochastic Optimization, Dynamic Optimization, Game Optimization, and Optimal Control, across three difficulty levels: Easy, Medium, and Hard. The experiments with 22 LLMs of different sizes reveal sharp performance degradation on hard problems, where even advanced models like GPT-5.2 and Gemini-3 struggle to exceed 27% accuracy. Through error analysis, we identify that modeling & logic errors remain the primary bottleneck. Consequently, we propose a Dual-View Auditor Agent that improves the accuracy of the LLM modeling process without introducing significant time overhead. OptiVerse will serve as a foundational platform for advancing LLMs in solving complex optimization challenges. |
| title | OptiVerse: A Comprehensive Benchmark towards Optimization Problem Solving |
| topic | Computation and Language |
| url | https://arxiv.org/abs/2604.21510 |