@inproceedings{xie-etal-2026-escaping,
    title = "Escaping the Sisyphus Dilemma: Experience Replay for Robust Text-to-Optimization Modeling",
    author = "Xie, Wantong  and
      Chen, Yinghao  and
      Hu, Yi-Xiang  and
      Wu, Feng  and
      Xu, Jieyang  and
      Zhang, Sijia  and
      Li, Xiangyang",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Findings of the {A}ssociation for {C}omputational {L}inguistics: {ACL} 2026",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.findings-acl.690/",
    pages = "14100--14116",
    ISBN = "979-8-89176-395-1",
    abstract = "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 primarily fetch static problem-model pairs as few-shot demonstrators, failing to capture the dynamic reasoning required to resolve execution failures. To bridge this gap, we propose \textbf{EOM}, a framework that implements Experience Replay to transform transient rectification steps into persistent knowledge. EOM distills interaction histories into Causal Correction Mappings, indexing both diagnostic insights and prohibitive traps. By utilizing a structure-aware retrieval mechanism that aligns semantic intent with abstract syntax trees and solver tracebacks, the system enables models to recall specific correction strategies for isomorphic errors. Extensive experiments across seven benchmarks demonstrate that EOM improves modeling accuracy by 8.45{\%} on complex tasks while reducing token consumption by 28.65{\%} and interaction turns by 25.82{\%}, validating the efficiency of a ``Rectify Once, Solve Many'' paradigm."
}