{"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/from-pixels-to-ui-actions-learning-to-follow","title":"From Pixels to UI Actions: Learning to Follow Instructions via Graphical User Interfaces","arxiv_id":"2306.00245","date":"2023-05-31","proceeding":"NeurIPS 2023 11","authors":["Peter Shaw","Mandar Joshi","James Cohan","Jonathan Berant","Panupong Pasupat","Hexiang Hu","Urvashi Khandelwal","Kenton Lee","Kristina Toutanova"],"abstract":"Much of the previous work towards digital agents for graphical user interfaces (GUIs) has relied on text-based representations (derived from HTML or other structured data sources), which are not always readily available. These input representations have been often coupled with custom, task-specific action spaces. This paper focuses on creating agents that interact with the digital world using the same conceptual interface that humans commonly use -- via pixel-based screenshots and a generic action space corresponding to keyboard and mouse actions. Building upon recent progress in pixel-based pretraining, we show, for the first time, that it is possible for such agents to outperform human crowdworkers on the MiniWob++ benchmark of GUI-based instruction following tasks.","url_abs":"https://arxiv.org/abs/2306.00245v2","url_pdf":"https://arxiv.org/pdf/2306.00245v2.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":"from-pixels-to-ui-actions-learning-to-follow","repo_url":"https://github.com/google-deepmind/pix2act","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"instruction-following","task_name":"Instruction Following"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2306.00245","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2306.00245"}},"developers":"https://syntology.ai/developers","read_at":"2026-09-24T18:15:14+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/google-deepmind/pix2act","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"unverified":9},"by_repo_kind":{"official":{"samples":9,"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":"7a8fbfbbda3d366a","entry":"get_bytes_feature","repo":"google-deepmind/pix2act","repo_kind":"official","path":"pix2act/common/tf_utils.py","file_url":"https://github.com/google-deepmind/pix2act/blob/HEAD/pix2act/common/tf_utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"7a8fbfbbda3d366a"}},{"code_sha256_prefix":"5219f685d8c77d1d","entry":"get_cursor","repo":"google-deepmind/pix2act","repo_kind":"official","path":"pix2act/common/render_utils.py","file_url":"https://github.com/google-deepmind/pix2act/blob/HEAD/pix2act/common/render_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5219f685d8c77d1d"}},{"code_sha256_prefix":"bd7544895c6d3aa9","entry":"get_text_feature","repo":"google-deepmind/pix2act","repo_kind":"official","path":"pix2act/common/tf_utils.py","file_url":"https://github.com/google-deepmind/pix2act/blob/HEAD/pix2act/common/tf_utils.py","link_basis":"plan_row","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"bd7544895c6d3aa9"}},{"code_sha256_prefix":"ebb6466594c5260f","entry":"image_to_png","repo":"google-deepmind/pix2act","repo_kind":"official","path":"pix2act/common/render_utils.py","file_url":"https://github.com/google-deepmind/pix2act/blob/HEAD/pix2act/common/render_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"ebb6466594c5260f"}},{"code_sha256_prefix":"5e85cc9e77027c04","entry":"is_float","repo":"google-deepmind/pix2act","repo_kind":"official","path":"pix2act/common/env_utils.py","file_url":"https://github.com/google-deepmind/pix2act/blob/HEAD/pix2act/common/env_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"5e85cc9e77027c04"}},{"code_sha256_prefix":"db719b0186363fc3","entry":"is_valid_coordinate","repo":"google-deepmind/pix2act","repo_kind":"official","path":"pix2act/common/env_utils.py","file_url":"https://github.com/google-deepmind/pix2act/blob/HEAD/pix2act/common/env_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"db719b0186363fc3"}},{"code_sha256_prefix":"83a66096381aeb52","entry":"normalize_reward","repo":"google-deepmind/pix2act","repo_kind":"official","path":"pix2act/tasks/miniwob/miniwob_env.py","file_url":"https://github.com/google-deepmind/pix2act/blob/HEAD/pix2act/tasks/miniwob/miniwob_env.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"83a66096381aeb52"}},{"code_sha256_prefix":"4d2647b6fe47d016","entry":"png_to_image","repo":"google-deepmind/pix2act","repo_kind":"official","path":"pix2act/common/render_utils.py","file_url":"https://github.com/google-deepmind/pix2act/blob/HEAD/pix2act/common/render_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"4d2647b6fe47d016"}},{"code_sha256_prefix":"535ec1bbd7e0de95","entry":"rel_x_y_to_x_y","repo":"google-deepmind/pix2act","repo_kind":"official","path":"pix2act/common/env_utils.py","file_url":"https://github.com/google-deepmind/pix2act/blob/HEAD/pix2act/common/env_utils.py","link_basis":"first_harvest_node","language":"python","status":"unverified","verification_level":0,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"535ec1bbd7e0de95"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}