# ARCH: Hierarchical Hybrid Learning for Long-Horizon Contact-Rich Robotic Assembly

arXiv: https://arxiv.org/abs/2409.16451 · HTML: https://mlsanity.com/paper/2409.16451/

## Key facts

- Cited by 10 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 24 Sep 2024.

## Built on by (most cited first, 10 of 10)

- [Dexterous Manipulation through Imitation Learning: A Survey](https://mlsanity.com/paper/2504.03515/) (2025)
- [SynapseRoute: An Auto-Route Switching Framework on Dual-State Large Language Model](https://mlsanity.com/paper/2507.02822/) (2025)
- [LEGS: Fine-Tuning Teleop-Free VLAs for Humanoid Loco-manipulation in an Embodied Gaussian Splatting World](https://mlsanity.com/paper/2606.01458/) (2026)
- [FurnitureVLA: Learning Long-Horizon Bimanual Furniture Assembly with Vision-Language-Action Model](https://mlsanity.com/paper/2607.01212/) (2026)
- [Learning Physical Interaction: A Survey of Tactile- and Force-aware Robot Learning](https://mlsanity.com/paper/2608.07558/) (2026)
- [Trace-Focused Diffusion Policy for Multi-Modal Action Disambiguation in Long-Horizon Robotic Manipulation](https://mlsanity.com/paper/2602.07388/) (2026)
- [ATLAS: An Annotation Tool for Long-horizon Robotic Action Segmentation](https://mlsanity.com/paper/2604.26637/) (2026)
- [Triplet2Track: A Hierarchical System with Object-Centric Representations for Reliable Long-Horizon Manipulation](https://mlsanity.com/paper/2608.22800/) (2026)
- [AlphaNIST: Emergent Assembly Skills from Binary Task Rewards](https://mlsanity.com/paper/2610.13354/) (2026)
- [Phase-Gated Constrained Reinforcement Learning for End-to-End Capture and Detumbling of Non-Cooperative Targets](https://mlsanity.com/paper/2610.15491/) (2026)

## Abstract (arXiv)

Generalizable long-horizon robotic assembly requires reasoning at multiple levels of abstraction. While end-to-end imitation learning (IL) is a promising approach, it typically requires large amounts of expert demonstration data and often struggles to achieve the high precision demanded by assembly tasks. Reinforcement learning (RL) approaches, on the other hand, have shown some success in high-precision assembly, but suffer from sample inefficiency, which limits their effectiveness in long-horizon tasks. To address these challenges, we propose a hierarchical modular approach, named Adaptive Robotic Compositional Hierarchy (ARCH), which enables long-horizon, high-precision robotic assembly in contact-rich settings. ARCH employs a hierarchical planning framework, including a low-level primitive library of parameterized skills and a high-level policy. The low-level primitive library includes essential skills for assembly tasks, such as grasping and inserting. These primitives consist of both RL and model-based policies. The high-level policy, learned via IL from a handful of demonstrations, without the need for teleoperation, selects the appropriate primitive skills and instantiates them with input parameters. We extensively evaluate our approach in simulation and on a real robotic manipulation platform. We show that ARCH generalizes well to unseen objects and outperforms baseline methods in terms of success rate and data efficiency. More details are available at: https://long-horizon-assembly.github.io.