Metraipolis › archive › dc_cf605e80a3fb

Evolving Agent Interfaces — arXiv:2610.28601

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.28601
License (as archived)
CC0-1.0
Archived
2026-10-21T07:07:13.104Z
SHA-256 of the archived text
fd4968903eabd8e6ff47f25c0ae8c2460ecd1ce0441a7f6a030b110b8d80d0fb
Stable URL of this page
https://metraipolis.com/documento/dc_cf605e80a3fb

How to cite

Evolving Agent Interfaces — arXiv:2610.28601 — arXiv (en), https://arxiv.org/abs/2610.28601 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_cf605e80a3fb (Metraipolis archive dc_cf605e80a3fb, sha256 fd4968903eabd8e6ff47f25c0ae8c2460ecd1ce0441a7f6a030b110b8d80d0fb)
BibTeX
@misc{dccf605e80a3fb,
  title = {Evolving Agent Interfaces — arXiv:2610.28601},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.28601},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_cf605e80a3fb; sha256 fd4968903eabd8e6ff47f25c0ae8c2460ecd1ce0441a7f6a030b110b8d80d0fb},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.28601. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Computer-use agents are limited by the interfaces humans give them. An agent may type a spreadsheet cell by cell when a single line of code would do, or print all two thousand lines of a file through a shell to find one function. Both the interfaces and the knowledge of when to use each are built by hand, which cannot keep pace with new applications, workflows, and models. We argue that interface design should itself be an agent capability. We introduce Agent S4, an autonomous computer-use scientist that builds Evolving Agent Interfaces from task experience. A meta-agent examines task agents' trajectories on synthetic training tasks, without success labels, and constructs and revises interfaces and usage knowledge in a repository. Population-based evolution then selects which repositories to develop further by their performance on validation tasks the meta-agent never sees, favoring changes that generalize beyond the seen tasks. On OSWorld V2, Agent S4, with Qwen3.8-27B and the evolved repository of interfaces, sets a new state of the art in open-source computer-use agents, reaching 21.3% binary score, 3.8 times the same model with fixed interfaces. This is above both GPT-5.5 (13.0%) and Claude Opus 4.8 (20.6%), at about 4.3% and 1.5% of their respective costs. On ScienceBoard, the evolved interfaces improve the success rate from 41.4% to 58.6% with the same model. These results suggest that useful interfaces can be evolved from experience, making autonomous interface design a source of improvement complementary to advances in models and harnesses. We open-source our code at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2610.28601 — 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 2026-10-21T07:05:43.494Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).