Research map / Large language models / Agents, code and math
SAC-Opt: Semantic Anchors for Iterative Correction in Optimization Modeling
Yansen Zhang, Qingcan Kang, Yujie chen, Yufei Wang, Xiongwei Han, Tao Zhong, Mingxuan Yuan, Chen Ma
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 semantic anchor-guided iterative correction (ablation) | SAC-Opt (GPT-4o) · ComplexLP | accuracy: 63.8% -> 79.6% | Improved |
| add semantic anchor-guided iterative correction (ablation) | SAC-Opt (GPT-4o) · IndustryOR | accuracy: 50.5% -> 63.8% | Improved |
| add solver-feedback code debugging after semantic correction (ablation) | SAC-Opt (GPT-4o) · ComplexLP | accuracy: 72.3% -> 79.6% | Improved |
| add semantic correction to a weaker open model (ablation) | Qwen2.5-72B-Instruct · IndustryOR | accuracy: 39.5% -> 45.7% | Improved |
| add semantic correction to a weaker open model (ablation) | Qwen2.5-72B-Instruct · ReSocratic | accuracy: 76.7% -> 85.9% | Improved |
| use LLM-based verification instead of similarity-based verification (ablation) | SAC-Opt · IndustryOR | accuracy: 52.9 -> 63.8 | Improved |
| use LLM-based verification instead of similarity-based verification (ablation) | SAC-Opt · ComplexLP | run time (s): 173.76 -> 40.96 | Improved |
| use LLM-based verification instead of similarity-based verification (ablation) | SAC-Opt · IndustryOR | debugging attempts: 0.31 ± 0.66 vs 0.16 ± 0.37 | No clear effect |
| add chain-of-thought prompting to standard prompting | GPT-4o baseline · EasyLP | accuracy: 70.3% -> 49.5% | Hurt |
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-0.3 — OptiMUS: Scalable Optimization Modeling with (MI)LP Solvers and Large Language Models (ICML 2024) · better on 4 of 4 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
- OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling (ICML 2025 · similarity 0.89)
- MM-OptBench: A Solver-Grounded Benchmark for Multimodal Optimization Modeling (NeurIPS 2026 · similarity 0.88)
- PEARL: Solver-in-the-Loop Interactive Optimization Modeling from Natural Language (NeurIPS 2026 · similarity 0.88)
- LLMOPT: Learning to Define and Solve General Optimization Problems from Scratch (ICLR 2025 · similarity 0.88)
- OptiBench Meets ReSocratic: Measure and Improve LLMs for Optimization Modeling (ICLR 2025 · similarity 0.88)
- REASONING COMPILER: LLM-Guided Optimizations for Efficient Model Serving (NeurIPS 2025 · similarity 0.87)
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.
