@inproceedings{wu-etal-2026-moec,
    title = "{M}o{EC}: A Memory-Routed Mixture-of-Experts Controller for Adaptive {M}inecraft Control",
    author = "Wu, Hui  and
      Xu, Chao  and
      Wang, Jianghui  and
      Liu, Ziqiong  and
      Li, Dong  and
      Dai, Yiwei  and
      Barsoum, Emad",
    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.1027/",
    pages = "22444--22459",
    ISBN = "979-8-89176-390-6",
    abstract = "Embodied agents in open-ended environments such as Minecraft increasingly adopt planner{--}controller architectures, with large language models acting as high-level planners. While planning has advanced rapidly, control remains underexplored. Existing systems commonly rely on a monolithic policy to execute subgoals across varying contexts, forcing incompatible behaviors into a shared parameter space and causing interference that scaling only partially mitigates. To address this, we propose MoEC, a Memory-Routed Mixture-of-Experts Controller for Adaptive Minecraft Control. MoEC routes via a subgoal-indexed, non-parametric expert memory and regulates capacity through failure-triggered expert growth and redundancy-aware consolidation. This design enables continual adaptation without full retraining, while maintaining parameter efficiency and with bounded inference cost. We evaluate MoEC on diverse and compositional Minecraft tasks, demonstrating significant gains in adaptability, robustness, and execution consistency over strong baselines, yielding a scalable and efficient alternative for open-ended control."
}