Metraipolis › archive › dc_407e653b05c2

Unified Agent: Managing Interactions across Devices — arXiv:2608.05729

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.05729
License (as archived)
CC0-1.0
Archived
2026-10-31T10:37:55.922Z
SHA-256 of the archived text
df8a02f19de4779a4c67d4a1824f22ce02d68aedc842d96a130812020d3181ae
Stable URL of this page
https://metraipolis.com/documento/dc_407e653b05c2

How to cite

Unified Agent: Managing Interactions across Devices — arXiv:2608.05729 — arXiv (en), https://arxiv.org/abs/2608.05729 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_407e653b05c2 (Metraipolis archive dc_407e653b05c2, sha256 df8a02f19de4779a4c67d4a1824f22ce02d68aedc842d96a130812020d3181ae)
BibTeX
@misc{dc407e653b05c2,
  title = {Unified Agent: Managing Interactions across Devices — arXiv:2608.05729},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.05729},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_407e653b05c2; sha256 df8a02f19de4779a4c67d4a1824f22ce02d68aedc842d96a130812020d3181ae},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.05729. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

As capabilities rapidly increase, AI agents can move from running inside one app to acting across a user's devices over time. Yet existing agent systems still fall short in this scenario. This is because observations are scattered across devices and moments, but mainstream systems are not designed around this fact: a single agent that treats devices as tools lacks effective state management for all devices across time, and multi-agent systems coordinate across agents but do not maintain the compact carried state a cross-device, cross-time request needs. We argue that the agent should maintain an effectively designed state that organizes engagement evidence, stated facts, and the standing request in a compact, action-ready form for deciding its action given the current observation. To compare state designs, we construct a benchmark of user-agent interaction across devices and time. We instantiate this principle in Unified Agent, a stateful agent that carries interaction evidence across devices and moments and uses it with the current observation to act. In the default setting, it significantly outperforms our adaptations of four published designs. Across changes in multimodal large language model (MLLM) family, capability, and reasoning effort, it remains ahead of all compared systems, demonstrating that the state-design advantage is robust across MLLM settings. Our code and data will be publicly available on GitHub.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-07 in cs.CV).
Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL); Computer Vision and Pattern Recognition (cs.CV); Human-Computer Interaction (cs.HC).
Pagina del lavoro: https://arxiv.org/abs/2608.05729 — 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 2026-10-31T10:23:31.084Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-07?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).