---
title: "Auriga Technical Report: A Task-Agnostic Agent Harness for Zero-Shot Embodied Manipulation"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2611.01112v1"
permalink: "https://feed.astralor.com/items/itm_5f6cd0e54df3edfb606d1cb5"
published: "2026-10-31T16:59:05.000Z"
score: 57
channel: "tech"
tags: ["AI Agent","OpenAI","多模态","Auriga Technical Report","Task-Agnostic Agent Harness","Zero-Shot Embodied Manipulation","Vision-language","RoboDojo"]
---

# Auriga Technical Report: A Task-Agnostic Agent Harness for Zero-Shot Embodied Manipulation

## 速览

Vision-language models can interpret instructions and plan manipulation tasks, yet struggle when acting directly as robot policies. On RoboDojo, a large planning-execution gap separates high-level task decisions from ph…

## 关键点

- Vision-language models can interpret instructions and plan manipulation tasks, yet struggle when acting directly as robot policies.
- On RoboDojo, a large planning-execution gap separates high-level task decisions from physical execution: removing arm execution raises GPT-6 Astra's success rate from 22.5% under the reference control interface to 76.2%.
- We present Auriga, a task-agnostic agent harness that closes 68.3% of this gap in zero-shot manipulation without target-task trials or resets.

## 全文

Vision-language models can interpret instructions and plan manipulation tasks, yet struggle when acting directly as robot policies. On RoboDojo, a large planning-execution gap separates high-level task decisions from physical execution: removing arm execution raises GPT-6 Astra's success rate from 22.5% under the reference control interface to 76.2%. We present Auriga, a task-agnostic agent harness that closes 68.3% of this gap in zero-shot manipulation without target-task trials or resets. In Auriga, the model makes all task decisions over an explicit task belief and acts through either direct tool calls or synthesized multi-step Python programs, while the harness supplies calibrated 3D measurements, finger-referenced dual-arm control, and a single admission gateway to the robot. Before motion, the model inspects a visual trajectory preview while simulation is paused; during execution, the harness checks declared stage tolerances and grasp bounds, stopping the robot on divergence and returning the measured discrepancy for in-place recovery. Developed across 13 cross-task capability iterations and frozen for evaluation, Auriga ranks first on the RoboDojo leaderboard with a 57.7% success rate (64.0 Score), more than doubling the reference harness on the same model, and remains first under scene randomization while learned policies drop by up to 33.9%. On RoboCasa365, the same frozen harness reaches a 73.2% success rate, outperforming VLA-assisted agents by up to 23.1% on composite tasks. Project page: https://auriga.stelledge.com/ Code: https://github.com/lose4578/Auriga

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_5f6cd0e54df3edfb606d1cb5