Metraipolis › archive › dc_edbcabb15d19
An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond — arXiv:2609.24170
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.24170
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-09T22:05:15.959Z
- SHA-256 of the archived text
9ca491ccca4b728c07a3fa19891930ca2c0f7ba03404a252665220a6b0f38005- Stable URL of this page
https://metraipolis.com/documento/dc_edbcabb15d19
How to cite
An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond — arXiv:2609.24170 — arXiv (en), https://arxiv.org/abs/2609.24170 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_edbcabb15d19 (Metraipolis archive dc_edbcabb15d19, sha256 9ca491ccca4b728c07a3fa19891930ca2c0f7ba03404a252665220a6b0f38005)
BibTeX
@misc{dcedbcabb15d19,
title = {An Unexpected Robot Policy: Early Evaluations of GPT-6 Astra on RoboDojo and Beyond — arXiv:2609.24170},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.24170},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_edbcabb15d19; sha256 9ca491ccca4b728c07a3fa19891930ca2c0f7ba03404a252665220a6b0f38005},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.24170. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Embodied AI systems are often organized into System 1 and System 2. System 1 is typically a pretrained policy that generates actions at high frequency, whereas System 2 is often instantiated as a vision-enabled language model for high-level planning. We ask whether a large language model (LLM) can act as the policy for robot manipulation without task-specific finetuning. We call this setting LLM as policy. We evaluate three LLMs on all 42 RoboDojo tasks and compare their scores with 40 public policies. Astra and GPT-5.5 use the official 50-episode-per-task protocol; DeepSeek-Flash uses 10 episodes per task. GPT-6 Astra achieves 22.48% average success rate and 28.97 Score over 2,100 trials, ranking above every public entry. Yet GPT-5.5 and DeepSeek-Flash reach only 0.88% and 1.92% average success rate with the same post-processing. We find that Astra exhibits a sharply polarized capability profile. It generalizes well to tasks that require semantic understanding but not high-precision control. In contrast, it performs poorly on tasks that require precision, dynamic control, or complex bimanual coordination. In-context experiments show no aggregate benefit from one-shot demonstrations, while selected interaction traces show within-episode corrections under perturbations. Overall, the evaluated LLMs vary substantially in manipulation performance. Astra stands out and provides initial evidence for the potential of a general-purpose manipulation model, although reliable precision and dynamic control remain limitations in the evaluated setting. Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-22 in cs.CV). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2609.24170 — 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 2026-10-09T21:45:21.000Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-22?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).