{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/navigating-the-digital-world-as-humans-do","title":"Navigating the Digital World as Humans Do: Universal Visual Grounding for GUI Agents","arxiv_id":"2410.05243","date":"2024-10-07","proceeding":null,"authors":["Boyu Gou","Ruohan Wang","Boyuan Zheng","Yanan Xie","Cheng Chang","Yiheng Shu","Huan Sun","Yu Su"],"abstract":"Multimodal large language models (MLLMs) are transforming the capabilities of graphical user interface (GUI) agents, facilitating their transition from controlled simulations to complex, real-world applications across various platforms. However, the effectiveness of these agents hinges on the robustness of their grounding capability. Current GUI agents predominantly utilize text-based representations such as HTML or accessibility trees, which, despite their utility, often introduce noise, incompleteness, and increased computational overhead. In this paper, we advocate a human-like embodiment for GUI agents that perceive the environment entirely visually and directly take pixel-level operations on the GUI. The key is visual grounding models that can accurately map diverse referring expressions of GUI elements to their coordinates on the GUI across different platforms. We show that a simple recipe, which includes web-based synthetic data and slight adaptation of the LLaVA architecture, is surprisingly effective for training such visual grounding models. We collect the largest dataset for GUI visual grounding so far, containing 10M GUI elements and their referring expressions over 1.3M screenshots, and use it to train UGround, a strong universal visual grounding model for GUI agents. Empirical results on six benchmarks spanning three categories (grounding, offline agent, and online agent) show that 1) UGround substantially outperforms existing visual grounding models for GUI agents, by up to 20% absolute, and 2) agents with UGround outperform state-of-the-art agents, despite the fact that existing agents use additional text-based input while ours only uses visual perception. These results provide strong support for the feasibility and promises of GUI agents that navigate the digital world as humans do.","url_abs":"https://arxiv.org/abs/2410.05243v1","url_pdf":"https://arxiv.org/pdf/2410.05243v1.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"navigating-the-digital-world-as-humans-do","repo_url":"https://github.com/OSU-NLP-Group/UGround","is_official":1,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":null}],"tasks":[{"task_slug":"natural-language-visual-grounding","task_name":"Natural Language Visual Grounding"},{"task_slug":"navigate","task_name":"Navigate"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[{"leaderboard":"/sota/natural-language-visual-grounding-on","task":"Natural Language Visual Grounding","dataset":"ScreenSpot","model":"UGround-V1-7B","rank_in_archive_order":1,"of":18,"metrics":{"Accuracy (%)":"86.34"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-visual-grounding-on","task":"Natural Language Visual Grounding","dataset":"ScreenSpot","model":"UGround-V1-2B","rank_in_archive_order":6,"of":18,"metrics":{"Accuracy (%)":"77.67"},"uses_additional_data":false},{"leaderboard":"/sota/natural-language-visual-grounding-on","task":"Natural Language Visual Grounding","dataset":"ScreenSpot","model":"UGround","rank_in_archive_order":9,"of":18,"metrics":{"Accuracy (%)":"73.3"},"uses_additional_data":false}],"syntology":{"syntology_url":"https://syntology.ai/paper/2410.05243","atlas_url":"https://app.syntology.ai/?focus=2410.05243","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2410.05243"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-25T09:33:49+00:00","read_at_is":"when the build read Syntology's graph, not when any sample ran","claim":"Per-sample execution status on synthesized fixtures; not a correctness claim about the paper. Samples come from repositories linked to the paper, official or community; repo_kind says which.","repos":[{"provenance":"external:paperswithcode_snapshot_2025-07-28","url":"https://github.com/OSU-NLP-Group/UGround","reach":null}],"summary":{"unverified":1},"by_repo_kind":{"official":{"samples":1,"ran":0,"repositories":1}},"repo_kind_vocabulary":{"official":"The archive marks this repository official for the paper","named_in_paper":"The archive records that the paper mentions this repository; it is not marked official","listed":"In the archive's code links for this paper, not marked official and not recorded as mentioned in the paper","found_in_text":"Syntology found this repository in the paper's own text; whether it is the authors' implementation is not asserted","community":"Not in the archive's code links for this paper; a community repository Syntology harvested"},"n_pointer_only_for_licence":0,"samples":[{"code_sha256_prefix":"7be1a8348d4ff760","entry":"score_rate","repo":"OSU-NLP-Group/UGround","repo_kind":"official","path":"online_evaluation/Mind2Web-Live-Results/calculate_scores.py","file_url":"https://github.com/OSU-NLP-Group/UGround/blob/HEAD/online_evaluation/Mind2Web-Live-Results/calculate_scores.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":"MISDECLARED","metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"7be1a8348d4ff760"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}