@inproceedings{hua-etal-2026-socia,
    title = "{SOCIA}-{EVO}: Automated Simulator Construction via Dual-Anchored Bi-Level Optimization",
    author = "Hua, Yuncheng  and
      Weatherhead, Sion  and
      Jafari, Mehdi  and
      Xue, Hao  and
      Salim, Flora D.",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1274/",
    pages = "27596--27634",
    ISBN = "979-8-89176-390-6",
    abstract = "Automated simulator construction requires distributional fidelity, distinguishing it from generic code generation. We identify two failure modes in long-horizon LLM agents: contextual drift and optimization instability arising from conflating structural and parametric errors. We propose SOCIA-EVO, a dual-anchored evolutionary framework. SOCIA-EVO introduces: (1) a static blueprint to enforce empirical constraints; (2) a bi-level optimization to decouple structural refinement from parameter calibration; and (3) a self-curating Strategy Playbook that manages remedial hypotheses via Bayesian-weighted retrieval. By falsifying ineffective strategies through execution feedback, SOCIA-EVO achieves robust convergence, generating simulators that are statistically consistent with observational data. SOCIA-EVO{'}s code and data are available here: https://github.com/cruiseresearchgroup/SOCIA/tree/evo."
}