Metraipolis › archive › dc_53789956a7db

Selective Knowledge Control for Continual GUI Agent Learning over Application Streams — arXiv:2609.06530

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.06530
License (as archived)
CC0-1.0
Archived
2026-10-16T15:07:05.462Z
SHA-256 of the archived text
1a71c5bdaa20fbaa419622ee8ac2c959569f8abcf73db7c14bdad157471576bd
Stable URL of this page
https://metraipolis.com/documento/dc_53789956a7db

How to cite

Selective Knowledge Control for Continual GUI Agent Learning over Application Streams — arXiv:2609.06530 — arXiv (en), https://arxiv.org/abs/2609.06530 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_53789956a7db (Metraipolis archive dc_53789956a7db, sha256 1a71c5bdaa20fbaa419622ee8ac2c959569f8abcf73db7c14bdad157471576bd)
BibTeX
@misc{dc53789956a7db,
  title = {Selective Knowledge Control for Continual GUI Agent Learning over Application Streams — arXiv:2609.06530},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.06530},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_53789956a7db; sha256 1a71c5bdaa20fbaa419622ee8ac2c959569f8abcf73db7c14bdad157471576bd},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.06530. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Continual learning is a crucial capability for Graphical User Interface (GUI) agents to adapt to evolving applications while retaining knowledge acquired from previous applications. Such application streams pose a challenging knowledge modeling problem: new applications often share underlying knowledge with past ones, yet also introduce specific knowledge that must not interfere with historical knowledge. In this paper, we propose activation-conditioned selective knowledge control, a lightweight method that achieves selective knowledge retention via neuron-level gradient manipulation. Our method maintains a compact historical knowledge state to protect highly activated MLP neurons that preserve previous knowledge. When a new application arrives, it performs real-time gradient surgery conditioned on forward activation. Concretely, the protected neurons are categorized into two types: unactivated neurons holding specific knowledge, whose gradients are truncated to prevent interference; and activated neurons holding shared knowledge, whose gradients are orthogonally projected to preserve stability while enabling adaptation. After each application stage, newly identified critical neurons are merged into the historical state for future learning. Empirical evaluations on multi-app sequential benchmark demonstrate that our method effectively mitigates catastrophic forgetting on prior applications while sustaining robust adaptation to new ones.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.06530 — 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 2026-10-16T14:49:57.096Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).