{
  "id": "2602.09856",
  "title": "Code2World: A GUI World Model via Renderable Code Generation",
  "authors": "Yuhao Zheng, Li'an Zhong, Yi Wang, Rui Dai, Kaikui Liu, Xiangxiang Chu, Linyuan Lv, Philip Torr, Kevin Qinghong Lin",
  "first_public": "2026-02-10",
  "first_public_source": "https://arxiv.org/abs/2602.09856",
  "venue": "arXiv",
  "arxiv": "2602.09856",
  "paper_url": "https://arxiv.org/abs/2602.09856",
  "lens": [
    "gui-planning"
  ],
  "related_terms": [
    "Code2World",
    "GUI world model",
    "renderable code",
    "next-screen prediction",
    "AndroidCode"
  ],
  "summary": "Predicts a GUI's next visual state by generating renderable code, and evaluates whether the predicted outcomes help mobile-agent navigation.",
  "contribution": "Constructs paired screen/action/code data and trains with rendered visual feedback to balance appearance and action consistency.",
  "limitations": "Uses generated code and a browser to predict screens for Android navigation.",
  "model_output": "Renderable UI code, converted into the predicted next screen.",
  "action_interface": "A current GUI observation and a proposed interaction, represented for the model with action descriptions and visual cues.",
  "state_memory": "Prediction conditions on the current screen and action; renderable structure represents the output interface.",
  "relationship": "Code2World cites NeuralOS in Section 2.2 and its bibliography.",
  "relationship_source": "https://arxiv.org/html/2602.09856v1#S2.SS2",
  "author_names": [
    "Yuhao Zheng",
    "Li'an Zhong",
    "Yi Wang",
    "Rui Dai",
    "Kaikui Liu",
    "Xiangxiang Chu",
    "Linyuan Lv",
    "Philip Torr",
    "Kevin Qinghong Lin"
  ],
  "record_url": "https://neural-os.com/reading-list/papers/2602.09856/",
  "legacy_record_url": "https://neural-os.com/reading-list/papers/#paper-2602-09856",
  "citation_date": "2026-02-10",
  "json_url": "https://neural-os.com/reading-list/papers/2602.09856/record.json",
  "markdown_url": "https://neural-os.com/reading-list/papers/2602.09856/index.md",
  "bibtex_url": "https://neural-os.com/reading-list/papers/2602.09856/citation.bib",
  "csl_url": "https://neural-os.com/reading-list/papers/2602.09856/citation.csl.json",
  "method_comparisons": [
    {
      "title": "Direct frame generation and renderable-code prediction",
      "text": "NeuralOS predicts desktop frames using learned state and a diffusion renderer. Code2World predicts a UI through code that is then rendered into a screen, and tests its usefulness for mobile navigation. Code2World cites NeuralOS in Section 2.2.",
      "source_ids": [
        "2507.08800",
        "2602.09856"
      ],
      "source_urls": [
        "https://arxiv.org/html/2507.08800v1",
        "https://arxiv.org/html/2602.09856v1#S2.SS2"
      ],
      "source_labels": [
        "Original NeuralOS paper",
        "Code2World Section 2.2"
      ],
      "topic_id": "gui-planning",
      "topic_label": "GUI prediction and planning",
      "topic_url": "https://neural-os.com/reading-list/guides/games-to-computers/#gui-prediction-and-planning"
    }
  ]
}