titleHeave-Ho: Decentralized Long-Horizon Multi-Humanoid Collaboration
authorsTing-Hsuan Chen, Siheng Zhao, Han Jiang, Qi Pan, Louison Lu, Jiaheng Luo, Henghui Bao, Yiyu Chen, Quan Nguyen, Yue Wang
date2026-11-17
venuearXiv (preprint, not peer reviewed)
idarXiv:2611.22275
affiliationUniversity of Southern California
upvotes21 (Hugging Face Daily Papers, 2026-11-19)
linksabs pdf hf code
cite
related3DCodeVerse: Exploring 3D Worlds as Code
SoloQ: Calibration-Free Quantization for Diffusion Language Models
KronQ: LLM Quantization via Kronecker-Factored Hessian
Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMs
An Exam for Active Observers
abstractCollaboration promises to extend humanoid capabilities beyond what individual robots can achieve. However, realizing this potential requires coordinated whole-body interactions, coherent long-horizon planning, and precise synchronization across robots. We introduce Heave-Ho, a decentralized framework for long-horizon collaborative multi-humanoid loco-manipulation. At the low level, we develop a multi-agent post-training framework that adapts a humanoid foundation tracking model to physically coupled interactions between humanoids, enabling coordinated decentralized control from local observations alone. At the high level, we train a vision-language planner and design a speech-based leader-follower coordination mechanism to synchronize decentralized execution without network communication. Trained with two identical humanoids, our system scales to teams of up to ten robots and generalizes to heterogeneous teams without retraining. To benchmark these capabilities, we introduce HH-Bench, comprising 12 tasks involving teams of 2 to 10 humanoids, including heterogeneous teams. Systematic evaluations show that Heave-Ho consistently outperforms baseline methods, while real-world experiments demonstrate robust decentralized collaboration across challenging tasks.

bibtex

@misc{chen2026heave,
  title={Heave-Ho: Decentralized Long-Horizon Multi-Humanoid Collaboration},
  author={Ting-Hsuan Chen and Siheng Zhao and Han Jiang and Qi Pan and Louison Lu and Jiaheng Luo and Henghui Bao and Yiyu Chen and Quan Nguyen and Yue Wang},
  year={2026},
  eprint={2611.22275},
  archivePrefix={arXiv},
  url={https://arxiv.org/abs/2611.22275}
}