AI Paper Atlas

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

ICML 2026 · Large language models › Agents, code and math · approach: LLM-guided program synthesis · 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 semantic anchor-guided iterative correction (ablation)SAC-Opt (GPT-4o) · ComplexLPaccuracy: 63.8% -> 79.6%Improved
add semantic anchor-guided iterative correction (ablation)SAC-Opt (GPT-4o) · IndustryORaccuracy: 50.5% -> 63.8%Improved
add solver-feedback code debugging after semantic correction (ablation)SAC-Opt (GPT-4o) · ComplexLPaccuracy: 72.3% -> 79.6%Improved
add semantic correction to a weaker open model (ablation)Qwen2.5-72B-Instruct · IndustryORaccuracy: 39.5% -> 45.7%Improved
add semantic correction to a weaker open model (ablation)Qwen2.5-72B-Instruct · ReSocraticaccuracy: 76.7% -> 85.9%Improved
use LLM-based verification instead of similarity-based verification (ablation)SAC-Opt · IndustryORaccuracy: 52.9 -> 63.8Improved
use LLM-based verification instead of similarity-based verification (ablation)SAC-Opt · ComplexLPrun time (s): 173.76 -> 40.96Improved
use LLM-based verification instead of similarity-based verification (ablation)SAC-Opt · IndustryORdebugging attempts: 0.31 ± 0.66 vs 0.16 ± 0.37No clear effect
add chain-of-thought prompting to standard promptingGPT-4o baseline · EasyLPaccuracy: 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.

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