{"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/gui-g1-understanding-r1-zero-like-training","title":"GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents","arxiv_id":"2505.15810","date":"2025-05-21","proceeding":null,"authors":["Yuqi Zhou","Sunhao Dai","Shuai Wang","Kaiwen Zhou","Qinqlin Jia","Junxu"],"abstract":"Recent Graphical User Interface (GUI) agents replicate the R1-Zero paradigm, coupling online Reinforcement Learning (RL) with explicit chain-of-thought reasoning prior to object grounding and thereby achieving substantial performance gains. In this paper, we first conduct extensive analysis experiments of three key components of that training pipeline: input design, output evaluation, and policy update-each revealing distinct challenges arising from blindly applying general-purpose RL without adapting to GUI grounding tasks. Input design: Current templates encourage the model to generate chain-of-thought reasoning, but longer chains unexpectedly lead to worse grounding performance. Output evaluation: Reward functions based on hit signals or box area allow models to exploit box size, leading to reward hacking and poor localization quality. Policy update: Online RL tends to overfit easy examples due to biases in length and sample difficulty, leading to under-optimization on harder cases. To address these issues, we propose three targeted solutions. First, we adopt a Fast Thinking Template that encourages direct answer generation, reducing excessive reasoning during training. Second, we incorporate a box size constraint into the reward function to mitigate reward hacking. Third, we revise the RL objective by adjusting length normalization and adding a difficulty-aware scaling factor, enabling better optimization on hard samples. Our GUI-G1-3B, trained on 17K public samples with Qwen2.5-VL-3B-Instruct, achieves 90.3% accuracy on ScreenSpot and 37.1% on ScreenSpot-Pro. This surpasses all prior models of similar size and even outperforms the larger UI-TARS-7B, establishing a new state-of-the-art in GUI agent grounding. The project repository is available at https://github.com/Yuqi-Zhou/GUI-G1.","url_abs":"https://arxiv.org/abs/2505.15810v1","url_pdf":"https://arxiv.org/pdf/2505.15810v1.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":"gui-g1-understanding-r1-zero-like-training","repo_url":"https://github.com/yuqi-zhou/gui-g1","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"pytorch","reach":{"status":"ok","spdx":"Apache-2.0"}}],"tasks":[{"task_slug":"answer-generation","task_name":"Answer Generation"},{"task_slug":"reinforcement-learning-1","task_name":"Reinforcement Learning (RL)"},{"task_slug":"visual-grounding","task_name":"Visual Grounding"}],"methods":[{"method_slug":"adopt","method_name":"ADOPT"}],"datasets_introduced":[],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":"https://app.syntology.ai/?focus=2505.15810","mcp":{"get_harvested_code_for_paper":{"arxiv_id":"2505.15810"}},"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/yuqi-zhou/gui-g1","reach":{"status":"ok","spdx":"Apache-2.0"}}],"summary":{"ran_fixture":1,"unverified":9},"by_repo_kind":{"official":{"samples":10,"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":"yuqi-zhou/gui-g1","repo_kind":"official","path":"src/open-r1-multimodal/local_scripts/create_vision_cot_data.py","file_url":"https://github.com/yuqi-zhou/gui-g1/blob/HEAD/src/open-r1-multimodal/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":"252870f138f5203f","entry":"evaluate_answer_similarity","repo":"yuqi-zhou/gui-g1","repo_kind":"official","path":"src/open-r1-multimodal/src/open_r1/grpo_jsonl.py","file_url":"https://github.com/yuqi-zhou/gui-g1/blob/HEAD/src/open-r1-multimodal/src/open_r1/grpo_jsonl.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":"252870f138f5203f"}},{"code_sha256_prefix":"317605c76a72fc89","entry":"extract_choice","repo":"yuqi-zhou/gui-g1","repo_kind":"official","path":"src/open-r1-multimodal/src/open_r1/grpo_jsonl.py","file_url":"https://github.com/yuqi-zhou/gui-g1/blob/HEAD/src/open-r1-multimodal/src/open_r1/grpo_jsonl.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":"317605c76a72fc89"}},{"code_sha256_prefix":"41c548a25e90eb39","entry":"extract_problem_solution","repo":"yuqi-zhou/gui-g1","repo_kind":"official","path":"src/open-r1-multimodal/local_scripts/prepare_hf_data.py","file_url":"https://github.com/yuqi-zhou/gui-g1/blob/HEAD/src/open-r1-multimodal/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":"e89f2eec0a18d4c2","entry":"format_reward","repo":"yuqi-zhou/gui-g1","repo_kind":"official","path":"src/open-r1-multimodal/src/open_r1/grpo.py","file_url":"https://github.com/yuqi-zhou/gui-g1/blob/HEAD/src/open-r1-multimodal/src/open_r1/grpo.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":"e89f2eec0a18d4c2"}},{"code_sha256_prefix":"58ab41ce28a94c62","entry":"gpt4o_query","repo":"yuqi-zhou/gui-g1","repo_kind":"official","path":"src/open-r1-multimodal/local_scripts/create_vision_cot_data.py","file_url":"https://github.com/yuqi-zhou/gui-g1/blob/HEAD/src/open-r1-multimodal/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":"306cc7b9dc8f750e","entry":"iou_reward","repo":"yuqi-zhou/gui-g1","repo_kind":"official","path":"src/open-r1-multimodal/src/open_r1/grpo_rec.py","file_url":"https://github.com/yuqi-zhou/gui-g1/blob/HEAD/src/open-r1-multimodal/src/open_r1/grpo_rec.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":"306cc7b9dc8f750e"}},{"code_sha256_prefix":"bdcc94560fb87f30","entry":"load_image_from_path","repo":"yuqi-zhou/gui-g1","repo_kind":"official","path":"src/open-r1-multimodal/local_scripts/prepare_hf_data.py","file_url":"https://github.com/yuqi-zhou/gui-g1/blob/HEAD/src/open-r1-multimodal/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":"c7446a6215a66f72","entry":"parse_json","repo":"yuqi-zhou/gui-g1","repo_kind":"official","path":"src/open-r1-multimodal/src/open_r1/grpo_rec.py","file_url":"https://github.com/yuqi-zhou/gui-g1/blob/HEAD/src/open-r1-multimodal/src/open_r1/grpo_rec.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":"c7446a6215a66f72"}},{"code_sha256_prefix":"f029d6b5f19d2885","entry":"process_single_item","repo":"yuqi-zhou/gui-g1","repo_kind":"official","path":"src/open-r1-multimodal/local_scripts/create_vision_cot_data.py","file_url":"https://github.com/yuqi-zhou/gui-g1/blob/HEAD/src/open-r1-multimodal/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"}}]},"arxiv_metadata":null,"syntology_extracted_results":null}