作者位次 #3/7ACL 2026Findings· Findings of ACL
Escaping the Sisyphus Dilemma: Experience Replay for Robust Text-to-Optimization Modeling
Wantong Xie · Yinghao Chen · Yi-Xiang Hu · Feng Wu · Jieyang Xu · Sijia Zhang · Xiang-Yang Li
摘要
Large Language Models have shown promise in translating natural language into executable optimization models, yet they often suffer from the Sisyphus Dilemma: a memoryless cycle where identical errors are repeated across structurally similar problems. Existing retrieval-augmented strategies prima...