{"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/empowering-llm-to-use-smartphone-for","title":"AutoDroid: LLM-powered Task Automation in Android","arxiv_id":"2308.15272","date":"2023-08-29","proceeding":null,"authors":["Hao Wen","Yuanchun Li","Guohong Liu","Shanhui Zhao","Tao Yu","Toby Jia-Jun Li","Shiqi Jiang","Yunhao Liu","Yaqin Zhang","Yunxin Liu"],"abstract":"Mobile task automation is an attractive technique that aims to enable voice-based hands-free user interaction with smartphones. However, existing approaches suffer from poor scalability due to the limited language understanding ability and the non-trivial manual efforts required from developers or end-users. The recent advance of large language models (LLMs) in language understanding and reasoning inspires us to rethink the problem from a model-centric perspective, where task preparation, comprehension, and execution are handled by a unified language model. In this work, we introduce AutoDroid, a mobile task automation system capable of handling arbitrary tasks on any Android application without manual efforts. The key insight is to combine the commonsense knowledge of LLMs and domain-specific knowledge of apps through automated dynamic analysis. The main components include a functionality-aware UI representation method that bridges the UI with the LLM, exploration-based memory injection techniques that augment the app-specific domain knowledge of LLM, and a multi-granularity query optimization module that reduces the cost of model inference. We integrate AutoDroid with off-the-shelf LLMs including online GPT-4/GPT-3.5 and on-device Vicuna, and evaluate its performance on a new benchmark for memory-augmented Android task automation with 158 common tasks. The results demonstrated that AutoDroid is able to precisely generate actions with an accuracy of 90.9%, and complete tasks with a success rate of 71.3%, outperforming the GPT-4-powered baselines by 36.4% and 39.7%. The demo, benchmark suites, and source code of AutoDroid will be released at url{https://autodroid-sys.github.io/}.","url_abs":"https://arxiv.org/abs/2308.15272v4","url_pdf":"https://arxiv.org/pdf/2308.15272v4.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":"empowering-llm-to-use-smartphone-for","repo_url":"https://github.com/mobilellm/autodroid","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"none","reach":{"status":"ok","spdx":"MIT"}}],"tasks":[{"task_slug":"language-modelling","task_name":"Language Modelling"}],"methods":[],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":"https://syntology.ai/paper/2308.15272","atlas_url":"https://app.syntology.ai/?focus=2308.15272","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2308.15272"}},"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/mobilellm/autodroid","reach":{"status":"ok","spdx":"MIT"}}],"summary":{"ran":4},"by_repo_kind":{"listed":{"samples":4,"ran":4,"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":"2915bdcc0dd313fc","entry":"get_id_from_view_desc","repo":"mobilellm/autodroid","repo_kind":"listed","path":"tools.py","file_url":"https://github.com/mobilellm/autodroid/blob/HEAD/tools.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"2915bdcc0dd313fc"}},{"code_sha256_prefix":"eaff9d242f5e9ce7","entry":"get_view_without_id","repo":"mobilellm/autodroid","repo_kind":"listed","path":"tools.py","file_url":"https://github.com/mobilellm/autodroid/blob/HEAD/tools.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"eaff9d242f5e9ce7"}},{"code_sha256_prefix":"874a827043f77340","entry":"insert_id_into_view","repo":"mobilellm/autodroid","repo_kind":"listed","path":"tools.py","file_url":"https://github.com/mobilellm/autodroid/blob/HEAD/tools.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":false,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"874a827043f77340"}},{"code_sha256_prefix":"dfad80aced080c6d","entry":"load_yaml_files","repo":"mobilellm/autodroid","repo_kind":"listed","path":"walk.py","file_url":"https://github.com/mobilellm/autodroid/blob/HEAD/walk.py","link_basis":"harvester_set","language":"python","status":"ran","verification_level":1,"contract_check":null,"metamorphic_tier":null,"behaviour_fingerprint":true,"licence":"MIT","inline_ok":true,"mcp_get_code":{"code_sha256":"dfad80aced080c6d"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}