[2602.02960] Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control

Computer Science > Robotics arXiv:2602.02960 (cs) [Submitted on 3 Feb 2026 (v1), last revised 27 Feb 2026 (this version, v2)] Title:Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control Authors:Quanquan Peng, Yunfeng Lin, Yufei Xue, Jiangmiao Pang, Weinan Zhang View a PDF of the paper titled Embodiment-Aware Generalist Specialist Distillation for Unified Humanoid Whole-Body Control, by Quanquan Peng and 4 other authors View PDF HTML (experimental) Abstract:Humanoid Whole-Body Controllers trained with reinforcement learning (RL) have recently achieved remarkable performance, yet many target a single robot embodiment. Variations in dynamics, degrees of freedom (DoFs), and kinematic topology still hinder a single policy from commanding diverse humanoids. Moreover, obtaining a generalist policy that not only transfers across embodiments but also supports richer behaviors-beyond simple walking to squatting, leaning-remains especially challenging. In this work, we tackle these obstacles by introducing EAGLE, an iterative generalist-specialist distillation framework that produces a single unified policy that controls multiple heterogeneous humanoids without per-robot reward tuning. During each cycle, embodiment-specific specialists are forked from the current generalist, refined on their respective robots, and new skills are distilled back into the generalist by training on the pooled embodiment set. Repeating this loop until performance conv...