Metraipolis › archive › dc_ade8d7b85aaa
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations — arXiv:2608.15930
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2608.15930
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-18T17:41:24.434Z
- SHA-256 of the archived text
121e0eee9a34da3d851a5d568d004a626fb1dbd6ddae52c3c990f7ae68db3670- Stable URL of this page
https://metraipolis.com/documento/dc_ade8d7b85aaa
How to cite
UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations — arXiv:2608.15930 — arXiv (en), https://arxiv.org/abs/2608.15930 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ade8d7b85aaa (Metraipolis archive dc_ade8d7b85aaa, sha256 121e0eee9a34da3d851a5d568d004a626fb1dbd6ddae52c3c990f7ae68db3670)
BibTeX
@misc{dcade8d7b85aaa,
title = {UI-Mate: Advancing Open-Weight Foundation GUI Agents with In-Context Demonstrations — arXiv:2608.15930},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2608.15930},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ade8d7b85aaa; sha256 121e0eee9a34da3d851a5d568d004a626fb1dbd6ddae52c3c990f7ae68db3670},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.15930. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Foundation GUI agents can automate complex digital tasks, but deployment is hindered by scarce and biased training data, ambiguous prompts, and unreliable execution. Routine workflows rely on user-specific tools and tacit conventions, so unstated instructions can produce arbitrary variations across runs. We present UI-Mate, a foundation GUI agent that integrates an environment-grounded training stack with in-context demonstration learning. UI-Mate makes three contributions: A Scalable Environment-Grounded Training Stack: A closed-loop data engine automates task generation, environment construction, rollout, filtering, capability balancing, SFT, and online RL across massively parallel environments via unified task-verifier bundles. In-Context Demonstration Learning: A mechanism that transforms multimodal demonstrations into flexible subtask-level workflows, follows relevant demonstrated steps, and re-plans from the live interface. OSWorkerBench Benchmark and Insights: A benchmark of 100 long-horizon office tasks across 41 applications that supports instruction-only and demonstration-guided evaluation. Its demonstration resources separate a 33-task self-demo setting, built from successful strong-agent rollouts of the same targets, from a 45-task variant-demo setting, built from human recordings of related but non-identical tasks. Experiments show that UI-Mate-27B sets a new open-weight state of the art on general computer-use benchmarks, scoring 77.0% on OSWorld-Verified and 66.2% on WindowsAgentArena. On OSWorkerBench, it reaches 41.0% strict success and 76.9% progress, outperforming its Qwen3.6-27B base by 17.7 and 24.5 points. On the 33-task self-demo subset, one demonstration raises strict success from 17.2% to 35.4% and progress from 67.9% to 81.1%, substantially improving long-horizon reliability. Project page: this https URL . Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-18 in cs.AI). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computer Vision and Pattern Recognition (cs.CV). Pagina del lavoro: https://arxiv.org/abs/2608.15930 — 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 2026-10-18T16:29:13.841Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-08-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).