Metraipolis › archive › dc_f90fbb644475

RoboARCade: Benchmarking Agentic Robot Control — arXiv:2611.08209

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.08209
License (as archived)
CC0-1.0
Archived
2026-11-06T14:54:12.265Z
SHA-256 of the archived text
a3457a40fda960bd9b6d02f390f7c034e6ee0c5e7ea2a9ffe78222aba5e8f6c5
Stable URL of this page
https://metraipolis.com/documento/dc_f90fbb644475

How to cite

RoboARCade: Benchmarking Agentic Robot Control — arXiv:2611.08209 — arXiv (en), https://arxiv.org/abs/2611.08209 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f90fbb644475 (Metraipolis archive dc_f90fbb644475, sha256 a3457a40fda960bd9b6d02f390f7c034e6ee0c5e7ea2a9ffe78222aba5e8f6c5)
BibTeX
@misc{dcf90fbb644475,
  title = {RoboARCade: Benchmarking Agentic Robot Control — arXiv:2611.08209},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.08209},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f90fbb644475; sha256 a3457a40fda960bd9b6d02f390f7c034e6ee0c5e7ea2a9ffe78222aba5e8f6c5},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.08209. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Improvements in multi-modal capabilities have enabled agents to act directly as robot policies, a setting we refer to as agentic robot control (ARC). We introduce RoboARCade, a benchmark of long-horizon manipulation tasks across three embodiments designed to test in-context adaptation, memory, and reasoning for precise control. The tasks build on existing open-source benchmarks, which we make harder by widening the range of initial conditions. RoboARCade is easy to use and extend: all tasks run on a single simulation backend, MuJoCo, each task is a self-contained data pack, and agents connect through interchangeable interfaces, so new tasks, agents, and interfaces can be added independently. The benchmark separates leading agents: GPT-6 Astra achieves 49.8% compared with 43.6% for Claude Fable 5.1, leaving substantial room for improvement. Comparing two interfaces, we find that a richer visual interface adds only 1.5 to 6.8 points at 1.7 to 2.3 times the cost. Failures stem mostly from choosing a poor manipulation strategy or executing a good one imprecisely, rarely from misunderstanding the scene, and agents incorrectly claim success on 24% to 39% of attempted subtasks. Agents can also improve without human input: one successful demonstration in context raises Astra's score from 53.5% to 73.0% on a five-task subset, and a prompt the agent writes and revises itself reaches 72.0%. Code, videos and full traces are available at this http URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.RO, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO).
Pagina del lavoro: https://arxiv.org/abs/2611.08209 — 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 2026-11-06T14:25:57.572Z dalla pagina https://arxiv.org/list/cs.RO/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).