@inproceedings{ren-etal-2026-caml,
    title = "{CAML}: A Conflict-Aware Molecular Language Model Merging Framework for Multi-Constraint Molecular Generation",
    author = "Ren, Xuanbai  and
      Tan, Luoda  and
      Liu, Pei  and
      Ma, Tengfei  and
      Fu, Xiangzheng  and
      Wang, Longyue  and
      Liu, Yiping  and
      Zeng, Xiangxiang",
    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.896/",
    pages = "19578--19594",
    ISBN = "979-8-89176-390-6",
    abstract = "Transfer learning has demonstrated efficacy in single-property constraint molecular generation. However, real-world drug discovery demands molecules to satisfy multiple property constraints. Existing paradigms often struggle with this challenge due to catastrophic forgetting or gradient conflicts. To address this, we propose a conflict-aware molecular language model merging framework (CAML). CAML generates multiple constraints molecular as a cooperative game among property-specific fine-tune models (expert models). Specifically, we formulate a Stability-Aware Covariance Matrix Adaptation Evolution Strategy (SACMA-ES) to dynamically optimize the fusion strategy. This algorithm searches for a Nash-equilibrium{--}like solution that minimizes conflicts among properties by exploring the optimal combination of the importance of the task parameter (intrinsic scale) and relative fusion weights of each expert (fusion coefficient), yielding a multi-constraint molecular property generation model without revisiting the training data. Extensive experiments demonstrate that CAML achieves state-of-the-art performance in complex multi-constraint scenarios. Our results validate that this training-free paradigm offers a robust and efficient solution for resolving intrinsic property conflicts in de novo molecular design."
}