RoboHarness: A Simple Harness Outperforms VLA and World Actions Models

Summary

The rise of large language models (LLMs) has opened a path toward generalist embodied AI, raising the question of how LLMs can act in the physical world.

Abstract Summary

The rise of large language models (LLMs) has opened a path toward generalist embodied AI, raising the question of how LLMs can act in the physical world. One straightforward approach is training the model to generate actions: collect robot-action data and video demonstration, refine LLM architecture with an action head, and train a vision-language-action (VLA) model at scale. However, we argue that coding agents have the potential to realize generalist embodied manipulation. All they need is a simple yet effective robot harness. We present RoboHarness: a robotic harness that gives LLM agents a visual-geometric control panel so that they can directly understand and invoke embodied tasks. With RoboHarness, Qwen3.8-Flash-Next outperforms state-of-the-art VLA models on BEHAVIOR Challenge 2025 tasks. The implementation will be released as open source.

Key Points

The rise of large language models (LLMs) has opened a path toward generalist embodied AI, raising the question of how LLMs can act in the physical world.
One straightforward approach is training the model to generate actions: collect robot-action data and video demonstration, refine LLM architecture with an action head, and train a vision-language-action (VLA) model at scale.
However, we argue that coding agents have the potential to realize generalist embodied manipulation
All they need is a simple yet effective robot harness
We present RoboHarness: a robotic harness that gives LLM agents a visual-geometric control panel so that they can directly understand and invoke embodied tasks.

Method

Lessons from coding agents show that: a minimal set of simple, orthogonal primitive tools outperforms a collection of predefined features and heavy scaffolding. Inspired by this principle, we argue that an LLM’s potential on embodied tasks is best unlocked by giving it the minimal primitive action tools rather than layers of engineered features.

We start from studying spatial relations between a gripper and objects it interacts with, therefore constructing the most elementary primitive action tools.

Method — RoboHarness: A Simple Harness Outperforms VLA and World Actions Models — Figure 1: RoboHarness overview: visual keypoints are tracked persistently, converted into geometric constraints, executed, and verified in a closed loop.

Proof: Completeness of the Keypoint-Constraint Representation

The three points on the robot gripper, namely the left fingertip, right fingertip, and gripper center, are intrinsic points that remain tracked throughout execution (Figure 4.1 ). The following results show that constraining their geometric relationships can represent arbitrary motion trajectories and interaction poses.

The elementary correspondence between a contact pose and a keypoint triple is given in Section 4.1 .

Proof: Completeness of the Keypoint-Constraint Representation — RoboHarness: A Simple Harness Outperforms VLA and World Actions Models — Figure 2: Visualization of the unified coordinate frame on two embodiments: BEHAVIOR R1 Pro ( Li et al., 2024 ) (left) and RoboDojo ARX X5 ( Chen et al., 2026 ) (right).

Experiments

We compare against state-of-the-art VLAs such as Galaxea G0.5 and $\pi_{0.5}$, evaluating both success rate and subgoal completion rate ( Liu et al., 2026 ; Black et al., 2025a ) . We additionally include the first- and second-place winners of the BEHAVIOR Challenge 2025 (RLC and Comet, respectively) ( Larchenko et al., 2025 ; Bai et al., 2025 ) , whose $q$-scores are reported on the official leaderboard.

The RoboHarness column is Qwen3.8-Flash-Next. Each entry is the mean $q$-score over five instances per task.

Experiments — RoboHarness: A Simple Harness Outperforms VLA and World Actions Models — Figure 3: Pipeline of the track_object tool: optical-flow keypoint tracking followed by depth back-projection into the robot coordinate frame.

Sources and Demonstrations

Figures are reproduced from Qu et al. See the full paper for experimental details and the project page, when the paper links one, for demonstrations and videos.