Metraipolis › archive › dc_8220e1db5fa2
Make Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot Tools — arXiv:2609.39018
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.39018
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-07T12:44:45.195Z
- SHA-256 of the archived text
052a109e776359dcadc2208e8f40e3b70a15633f18b66bf11263c7a580178c62- Stable URL of this page
https://metraipolis.com/documento/dc_8220e1db5fa2
How to cite
Make Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot Tools — arXiv:2609.39018 — arXiv (en), https://arxiv.org/abs/2609.39018 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_8220e1db5fa2 (Metraipolis archive dc_8220e1db5fa2, sha256 052a109e776359dcadc2208e8f40e3b70a15633f18b66bf11263c7a580178c62)
BibTeX
@misc{dc8220e1db5fa2,
title = {Make Code as Policy Great Again: Frontier Agents Write, Call, and Evolve Robot Tools — arXiv:2609.39018},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.39018},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_8220e1db5fa2; sha256 052a109e776359dcadc2208e8f40e3b70a15633f18b66bf11263c7a580178c62},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.39018. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Frontier models can control robots, but reasoning through every reach, grasp, and retreat makes manipulation slow and token-intensive. We revisit code as policy with a different division of labor: models build executable tools, code handles multi-phase motions, and models decide what to do next. We introduce URAI (Universal Robot-Agent Interface), which couples a programming agent that constructs robot tools with an execution agent that uses them in a feedback loop. The programming agent writes reusable and task-specific tools from task intent and refines them through execution feedback and human guidance. The execution agent selects and parameterizes these tools from current observations; each call runs a complete motion locally before returning control to the agent. Unlike delegating subsequent decisions to a generated program, this design retains model-level decision-making between tool executions. Validated tool revisions persist across episodes without updating foundation-model weights, and a shared GUI and API make the same tools available to humans and agents. Across five RoboDojo tasks and four frozen execution agents, URAI raises aggregate success from 18.0% to 53.0% relative to direct fingertip control, with the largest gain on Swap Blocks; with the same tools, a program written in advance reaches only 24% against 56% for two agents deciding after each call. Three of the four agents also finish episodes 1.3-1.5 times faster with 1.5-1.7 times fewer execution-agent output tokens; DeepSeek-V4-Flash's cost barely changes. We further evaluate URAI on seven real-world AgileX dual-arm tasks, spanning object manipulation, cloth folding, and human-interactive tic-tac-toe. URAI connects the coding and decision-making capabilities of frontier agents, organizing robot control around reusable tools that agents can both invoke and revise. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-10-01 in cs.AI). Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2609.39018 — 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 2026-10-07T12:14:13.997Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-10-01?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).