{"paper":{"title":"MobileDreamer: Generative Sketch World Model for GUI Agent","arxiv_id":"2601.04035","primary_cat":"cs.AI","submitted_at":"2026-01-07T15:51:44+00:00","version_compiled":"v2"},"notice":"Every quoted sentence is the authors' text from the arXiv listing abstract. Labels and probabilities are the outputs of classifier-1.13.0 on the question bank abstract-p1-20260923, exactly as returned. No sentence in this record was written by a language model.","schema":"pith.compiled-record/v0","status":"compiled","abstract":{"source":"arXiv listing abstract v2","sentences":[{"i":0,"p":1.0,"id":"s0","own":false,"role":"background","text":"Mobile GUI agents have shown strong potential in real-world automation and practical applications.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.06,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.0,"background":1.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":1,"p":0.66,"id":"s1","own":false,"role":"gap","text":"However, most existing agents remain reactive, making decisions mainly from current screen, which limits their performance on long-horizon tasks.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.06,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.17,"role_probabilities":{"gap":0.66,"method":0.0,"result":0.0,"background":0.31,"limitation":0.03,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":2,"p":0.9,"id":"s2","own":false,"role":"background","text":"Building a world model from repeated interactions enables forecasting action outcomes and supports better decision making for mobile GUI agents.","hedge":{"p":0.87,"label":"asserted"},"own_p":0.09,"main_claim_p":0.09,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.04,"method":0.03,"result":0.0,"background":0.9,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.01}},{"i":3,"p":0.54,"id":"s3","own":false,"role":"background","text":"This is challenging because the model must predict post-action states with spatial awareness while remaining efficient enough for practical deployment.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.06,"main_claim_p":0.02,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.42,"method":0.0,"result":0.0,"background":0.54,"limitation":0.04,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":4,"p":0.99,"id":"s4","own":true,"role":"contribution","text":"In this paper, we propose MobileDreamer, an efficient world-model-based lookahead framework to equip the GUI agents based on the future imagination provided by the world model.","hedge":{"p":0.99,"label":"asserted"},"own_p":0.87,"main_claim_p":0.19,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.01,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.99,"interpretation":0.0}},{"i":5,"p":0.83,"id":"s5","own":true,"role":"method","text":"It consists of textual sketch world model and rollout imagination for GUI agent.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.65,"main_claim_p":0.04,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.83,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.17,"interpretation":0.0}},{"i":6,"p":0.98,"id":"s6","own":true,"role":"method","text":"Textual sketch world model forecasts post-action states through a learning process to transform digital images into key task-related sketches, and designs a novel order-invariant learning strategy to preserve the spatial information of GUI elements.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.9,"main_claim_p":0.05,"quantitative":false,"quantitative_p":0.03,"role_probabilities":{"gap":0.0,"method":0.98,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.02,"interpretation":0.0}},{"i":7,"p":0.95,"id":"s7","own":true,"role":"method","text":"The rollout imagination strategy for GUI agent optimizes the action-selection process by leveraging the prediction capability of world model.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.73,"main_claim_p":0.06,"quantitative":false,"quantitative_p":0.02,"role_probabilities":{"gap":0.0,"method":0.95,"result":0.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.05,"interpretation":0.0}},{"i":8,"p":1.0,"id":"s8","own":true,"role":"result","text":"Experiments on Android World show that MobileDreamer achieves state-of-the-art performance and improves task success by 5.25%.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.96,"main_claim_p":0.65,"quantitative":true,"quantitative_p":0.99,"role_probabilities":{"gap":0.0,"method":0.0,"result":1.0,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.0}},{"i":9,"p":0.99,"id":"s9","own":true,"role":"result","text":"World model evaluations further verify that our textual sketch modeling accurately forecasts key GUI elements.","hedge":{"p":1.0,"label":"asserted"},"own_p":0.95,"main_claim_p":0.12,"quantitative":false,"quantitative_p":0.05,"role_probabilities":{"gap":0.0,"method":0.0,"result":0.99,"background":0.0,"limitation":0.0,"future_work":0.0,"contribution":0.0,"interpretation":0.01}}]},"compiled":{"main_claim":{"p":0.98,"text":"Experiments on Android World show that MobileDreamer achieves state-of-the-art performance and improves task success by 5.25%.","location":"abstract s8","hedge_strength":{"p":1.0,"label":"asserted"}},"provenance":{"route":{"via":"TypeSafe API","model":"classifier-1.13.0","endpoint":"https://api.typesafe.ai/v1/systemone","provider":"TypeSafe"},"packing":"one request per paper","requests":1,"input_tokens":7406,"cost_usd_reported":0.0},"compiled_at":"2026-09-23","bank_version":"abstract-p1-20260923","model_version":"classifier-1.13.0","abstract_states":{"claims_first":0.06,"states_limitation":0.12,"human_participants":0.05,"controlled_comparison":0.31,"randomized_assignment":0.01,"states_quantitative_result":0.99,"compares_with_prior_results":0.8,"mentions_code_or_data_availability":0.03},"evidential_basis":{"p":1.0,"value":"observation or experiment","probabilities":{"argument":0.0,"literature":0.0,"proof_or_derivation":0.0,"analysis_of_existing_data":0.0,"observation_or_experiment":1.0,"simulation_or_computation":0.0}},"contribution_type":{"p":1.0,"value":"method or tool","probabilities":{"review":0.0,"method_or_tool":1.0,"empirical_study":0.0,"simulation_study":0.0,"theoretical_result":0.0,"dataset_or_benchmark":0.0,"position_or_commentary":0.0}},"contribution_statement":{"p":0.96,"text":"In this paper, we propose MobileDreamer, an efficient world-model-based lookahead framework to equip the GUI agents based on the future imagination provided by the world model.","location":"abstract s4"}},"coverage":{"tier":"abstract","levels_run":["P abstract"],"not_examined":["full text","figures and tables","references and citing sentences","relations to other papers"],"sources_read":["arXiv listing abstract v2"],"levels_not_run":["S sections","T body sentences","C citations","R cross-paper relations"],"sentences_examined":10,"sentences_in_abstract":10},"measured_accuracy":{"url":"https://pith.science/accuracy","measured_on":"2026-10-02","method":"two independent model families labelled a fresh random sample blind; the figure is how often the published label matches their consensus","sentence_role_agreement":0.92,"main_claim_agreement":0.908,"typed_citation_agreement":0.933,"typed_citation_agreement_95_interval":[0.917,0.945],"review_comments_accurate":0.758,"review_comments_accurate_95_interval":[0.684,0.82],"review_caught_admitted_error_found_or_related":0.448,"review_comments_judged":{"judged_by":["gpt-5.6-luna","grok-4.7"],"judged_against":"Pith's own text copy of each paper: text extracted from the PDF, the first 90,000 characters","measured_on":"2026-10-04","accurate":113,"decided":149,"sampled_reviews":200,"split_by_lane":false,"by_lane":"https://pith.science/accuracy#by-lane"}}}