Robotic imitation learning faces a fundamental trade-off between modeling long-horizon dependencies and enabling fine-grained closed-loop control. Existing fixed-frequency action chunking approaches struggle to achieve both. Building on this insight, we propose HiPolicy, a hierarchical multi-frequency action chunking framework that jointly predicts action sequences at different frequencies to capture both coarse high-level plans and precise reactive motions. We extract and fuse hierarchical features from history observations aligned to each frequency for multi-frequency chunk generation, and introduce an entropy-guided execution mechanism that adaptively balances long-horizon planning with fine-grained control based on action uncertainty. Experiments on diverse simulated benchmarks and real-world manipulation tasks show that HiPolicy can be seamlessly integrated into existing 2D and 3D generative policies, delivering consistent improvements in performance while significantly enhancing execution efficiency.
@article{arxiv.2604.06067,
title = {HiPolicy: Hierarchical Multi-Frequency Action Chunking for Policy Learning},
author = {Jiyao Zhang and Zimu Han and Junhan Wang and Xionghao Wu and Shihong Lin and Jinzhou Li and Hongwei Fan and Ruihai Wu and Dongjiang Li and Hao Dong},
journal= {arXiv preprint arXiv:2604.06067},
year = {2026}
}