{"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/ui-r1-enhancing-action-prediction-of-gui","title":"UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning","arxiv_id":"2503.21620","date":"2025-03-27","proceeding":null,"authors":["Zhengxi Lu","Yuxiang Chai","Yaxuan Guo","Xi Yin","Liang Liu","Hao Wang","Han Xiao","Shuai Ren","Guanjing Xiong","Hongsheng Li"],"abstract":"The recent DeepSeek-R1 has showcased the emergence of reasoning capabilities in LLMs through reinforcement learning (RL) with rule-based rewards. Despite its success in language models, its application in multi-modal domains, particularly in graphic user interface (GUI) agent tasks, remains under-explored. To address this issue, we propose UI-R1, the first framework to explore how rule-based RL can enhance the reasoning capabilities of multimodal large language models (MLLMs) for GUI action prediction tasks. Specifically, UI-R1 introduces a novel rule-based action reward, enabling model optimization via policy-based algorithms such as Group Relative Policy Optimization (GRPO). For efficient training, we curate a small yet high-quality dataset of 136 challenging tasks, encompassing five common action types on mobile devices. Experimental results demonstrate that our proposed UI-R1-3B achieves significant improvements over the base model (i.e. Qwen2.5-VL-3B) on both in-domain (ID) and out-of-domain (OOD) tasks, with average accuracy gains of 22.1% on ScreenSpot, 6.0% on ScreenSpot-Pro, and 12.7% on ANDROIDCONTROL. Furthermore, UI-R1-3B delivers competitive performance compared to larger models (e.g., OS-Atlas-7B) trained via supervised fine-tuning (SFT) on 76K samples. We additionally develop an optimized version, UI-R1-E-3B, which significantly improves both grounding efficiency and accuracy. These results underscore the potential of rule-based reinforcement learning to advance GUI understanding and control, paving the way for future research in this domain. Code website: https://github.com/lll6gg/UI-R1.","url_abs":"https://arxiv.org/abs/2503.21620v4","url_pdf":"https://arxiv.org/pdf/2503.21620v4.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":"ui-r1-enhancing-action-prediction-of-gui","repo_url":"https://github.com/lll6gg/ui-r1","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"model-optimization","task_name":"Model Optimization"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"}],"methods":[{"method_slug":"base","method_name":"BASE"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2503.21620","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2503.21620"}},"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/lll6gg/ui-r1","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"unverified":11},"by_repo_kind":{"official":{"samples":12,"ran":1,"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":"3f31b48fd862935d","entry":"get_image_data_url","repo":"lll6gg/ui-r1","repo_kind":"official","path":"src/ui_r1/local_scripts/create_vision_cot_data.py","file_url":"https://github.com/lll6gg/ui-r1/blob/HEAD/src/ui_r1/local_scripts/create_vision_cot_data.py","link_basis":"harvester_set","language":"python","status":"ran_fixture","verification_level":1,"contract_check":"RAISES","metamorphic_tier":"deterministic","behaviour_fingerprint":false,"licence":"Apache-2.0","inline_ok":true,"mcp_get_code":{"code_sha256":"3f31b48fd862935d"}},{"code_sha256_prefix":"0973f0f093e870b6","entry":"extract_action","repo":"lll6gg/ui-r1","repo_kind":"official","path":"src/ui_r1/src/open_r1/grpo_json_action_coord-dast.py","file_url":"https://github.com/lll6gg/ui-r1/blob/HEAD/src/ui_r1/src/open_r1/grpo_json_action_coord-dast.py","link_basis":"harvester_set","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":"0973f0f093e870b6"}},{"code_sha256_prefix":"d73a25686eea74ad","entry":"extract_bbox","repo":"lll6gg/ui-r1","repo_kind":"official","path":"evaluation/eval_ss_pro.py","file_url":"https://github.com/lll6gg/ui-r1/blob/HEAD/evaluation/eval_ss_pro.py","link_basis":"harvester_set","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":"d73a25686eea74ad"}},{"code_sha256_prefix":"035f888a03e23312","entry":"extract_bbox","repo":"lll6gg/ui-r1","repo_kind":"official","path":"src/ui_r1/src/open_r1/grpo_json_action_coord-dast.py","file_url":"https://github.com/lll6gg/ui-r1/blob/HEAD/src/ui_r1/src/open_r1/grpo_json_action_coord-dast.py","link_basis":"harvester_set","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":"035f888a03e23312"}},{"code_sha256_prefix":"65a33c4833de06e2","entry":"extract_coord","repo":"lll6gg/ui-r1","repo_kind":"official","path":"evaluation/eval_ss_pro.py","file_url":"https://github.com/lll6gg/ui-r1/blob/HEAD/evaluation/eval_ss_pro.py","link_basis":"harvester_set","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":"65a33c4833de06e2"}},{"code_sha256_prefix":"fd4b791e36daf2e0","entry":"extract_coord","repo":"lll6gg/ui-r1","repo_kind":"official","path":"src/ui_r1/src/open_r1/grpo_json_action_coord-dast.py","file_url":"https://github.com/lll6gg/ui-r1/blob/HEAD/src/ui_r1/src/open_r1/grpo_json_action_coord-dast.py","link_basis":"harvester_set","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":"fd4b791e36daf2e0"}},{"code_sha256_prefix":"41c548a25e90eb39","entry":"extract_problem_solution","repo":"lll6gg/ui-r1","repo_kind":"official","path":"src/ui_r1/local_scripts/prepare_hf_data.py","file_url":"https://github.com/lll6gg/ui-r1/blob/HEAD/src/ui_r1/local_scripts/prepare_hf_data.py","link_basis":"harvester_set","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":"41c548a25e90eb39"}},{"code_sha256_prefix":"58ab41ce28a94c62","entry":"gpt4o_query","repo":"lll6gg/ui-r1","repo_kind":"official","path":"src/ui_r1/local_scripts/create_vision_cot_data.py","file_url":"https://github.com/lll6gg/ui-r1/blob/HEAD/src/ui_r1/local_scripts/create_vision_cot_data.py","link_basis":"harvester_set","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":"58ab41ce28a94c62"}},{"code_sha256_prefix":"bdcc94560fb87f30","entry":"load_image_from_path","repo":"lll6gg/ui-r1","repo_kind":"official","path":"src/ui_r1/local_scripts/prepare_hf_data.py","file_url":"https://github.com/lll6gg/ui-r1/blob/HEAD/src/ui_r1/local_scripts/prepare_hf_data.py","link_basis":"harvester_set","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":"bdcc94560fb87f30"}},{"code_sha256_prefix":"3a64cfbe91e08c2e","entry":"process_ref_dir","repo":"lll6gg/ui-r1","repo_kind":"official","path":"evaluation/eval_ss_pro.py","file_url":"https://github.com/lll6gg/ui-r1/blob/HEAD/evaluation/eval_ss_pro.py","link_basis":"harvester_set","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":"3a64cfbe91e08c2e"}},{"code_sha256_prefix":"f029d6b5f19d2885","entry":"process_single_item","repo":"lll6gg/ui-r1","repo_kind":"official","path":"src/ui_r1/local_scripts/create_vision_cot_data.py","file_url":"https://github.com/lll6gg/ui-r1/blob/HEAD/src/ui_r1/local_scripts/create_vision_cot_data.py","link_basis":"harvester_set","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":"f029d6b5f19d2885"}},{"code_sha256_prefix":"a50444314d796645","entry":"smart_resize","repo":"lll6gg/ui-r1","repo_kind":"official","path":"src/ui_r1/src/open_r1/trainer/DAST_grpo_trainer.py","file_url":"https://github.com/lll6gg/ui-r1/blob/HEAD/src/ui_r1/src/open_r1/trainer/DAST_grpo_trainer.py","link_basis":"harvester_set","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":"a50444314d796645"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}