RoboHarness: Heterogeneous Policy Orchestration Boosts Long-Horizon Robotics to 95.2%

机器之心 · wechat · 2026-08-03

In embodied AI, control policies like VLA, RL, and TAMP each have distinct strengths, but a single model struggles with complex tasks requiring semantic understanding, geometric precision, and long-horizon reasoning simultaneously.

The paper introduces RoboHarness, a framework that shifts focus from waiting for a single general-purpose model to orchestrating heterogeneous policies. It solves two key challenges:

Experiments show that in zero-shot evaluations on the long-horizon LIBERO-LoHo benchmark, RoboHarness achieves a complete success rate of 95.2%, significantly outperforming hierarchical decomposition methods using LLMs or world models (max 64.8%).

Original post →

More from Embodied

Embodied channel →