Metraipolis › archive › dc_28fa093e9db7

RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory — arXiv:2610.42141

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.42141
License (as archived): CC0-1.0
Archived: 2026-11-03T07:43:34.030Z
SHA-256 of the archived text: 4d192bf2e0e8a29df853065a635cf4b77dea187323325a1df818aa3a4fd4f302
Stable URL of this page: https://metraipolis.com/documento/dc_28fa093e9db7

How to cite

RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory — arXiv:2610.42141 — arXiv (en), https://arxiv.org/abs/2610.42141 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_28fa093e9db7 (Metraipolis archive dc_28fa093e9db7, sha256 4d192bf2e0e8a29df853065a635cf4b77dea187323325a1df818aa3a4fd4f302)

BibTeX

@misc{dc28fa093e9db7,
  title = {RoboArchitect: Automating the Design of Robotic Agents with Persistent Memory — arXiv:2610.42141},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.42141},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_28fa093e9db7; sha256 4d192bf2e0e8a29df853065a635cf4b77dea187323325a1df818aa3a4fd4f302},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.42141. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Recent work shows that a frozen robot policy performs far better inside an agent harness, where control code decides when to query the policy, consult vision tools, or command the arm directly. Yet today these harnesses are built by hand and redesigned for each new robot or benchmark. We show that harness design can be automated, offering a strong alternative to finetuning on a novel setup. In RoboArchitect, a coding model observes a robot's rollouts, diagnoses failures, and iteratively revises the harness around the frozen policy. The harness evolves on a set of episodes for its optimization and is evaluated on held-out scenes and tasks. Without updating any model weights, RoboArchitect raises average success from 9.7% to 43.3% on unseen scenes (4.5x) and from 12.7% to 40.2% on unseen tasks (3.2x), across multiple benchmarks and policies. The gains are largest where the benchmark is far from the policy's training data: wrapping a general-purpose policy, the evolved harness yields a specialist that often outperforms even the finetuned version. Intuitive control strategies are automatically designed, such as lifting a jammed arm clear or reaching in horizontally when an obstacle blocks the way from above. The harness also evolves its own persistent memory, carrying learned experience, such as effective grasp depths, into later decisions. These results suggest that substantial headroom in robotic manipulation lies in the agent harness, and its design can be effectively automated and optimized without weight updates.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Robotics (cs.RO) ; Artificial Intelligence (cs.AI); Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.42141 — 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 2026-11-03T07:39:37.411Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).