Metraipolis › archive › dc_4bc0b430edcc

Auriga Technical Report: A Task-Agnostic Agent Harness for Zero-Shot Embodied Manipulation — arXiv:2611.01112

Source: arXiv (en)
Original: https://arxiv.org/abs/2611.01112
License (as archived): CC0-1.0
Archived: 2026-11-03T10:35:41.595Z
SHA-256 of the archived text: 94262805022229a48076ca4b42700237c1be3aea64e1b8e958b534b188b751e0
Stable URL of this page: https://metraipolis.com/documento/dc_4bc0b430edcc

How to cite

Auriga Technical Report: A Task-Agnostic Agent Harness for Zero-Shot Embodied Manipulation — arXiv:2611.01112 — arXiv (en), https://arxiv.org/abs/2611.01112 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4bc0b430edcc (Metraipolis archive dc_4bc0b430edcc, sha256 94262805022229a48076ca4b42700237c1be3aea64e1b8e958b534b188b751e0)

BibTeX

@misc{dc4bc0b430edcc,
  title = {Auriga Technical Report: A Task-Agnostic Agent Harness for Zero-Shot Embodied Manipulation — arXiv:2611.01112},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.01112},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4bc0b430edcc; sha256 94262805022229a48076ca4b42700237c1be3aea64e1b8e958b534b188b751e0},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.01112. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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: this https URL Code: this https URL

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.01112 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T10:29:48.744Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).