{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:T2ETCQLGZBGBUS4OKRR2PITHLX","short_pith_number":"pith:T2ETCQLG","schema_version":"1.0","canonical_sha256":"9e89314166c84c1a4b8e5463a7a2675dd9a4e1cb2bfef1aa6a739429056839c0","source":{"kind":"arxiv","id":"2508.15144","version":2},"attestation_state":"computed","paper":{"title":"Mobile-Agent-v3: Fundamental Agents for GUI Automation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fei Huang, Feiyu Gao, Haiyang Xu, Haowei Liu, Jiabo Ye, Jingren Zhou, Jitong Liao, Junjie Cao, Junyang Wang, Ming Yan, Qi Zheng, Xi Zhang, Zhaoqing Zhu, Zhengxi Lu, Ziwei Zheng","submitted_at":"2025-08-21T00:39:12Z","abstract_excerpt":"This paper introduces GUI-Owl, a foundational GUI agent model that achieves state-of-the-art performance among open-source end-to-end models on ten GUI benchmarks across desktop and mobile environments, covering grounding, question answering, planning, decision-making, and procedural knowledge. GUI-Owl-7B achieves 66.4 on AndroidWorld and 29.4 on OSWorld. Building on this, we propose Mobile-Agent-v3, a general-purpose GUI agent framework that further improves performance to 73.3 on AndroidWorld and 37.7 on OSWorld, setting a new state-of-the-art for open-source GUI agent frameworks. GUI-Owl in"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2508.15144","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-08-21T00:39:12Z","cross_cats_sorted":[],"title_canon_sha256":"aa2d215ebf801db779f46792c3c0949558bf608bd444a8f475c132ef7c596300","abstract_canon_sha256":"37aab0ec22cb1d2f11c6d12e30c9fa40728ea65c9a897fc2bda7f2ecae3a6f51"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T11:54:46.555528Z","signature_b64":"wRm6GRCWbaR29Z+3AmmPKwaltiLCF+JucGa5ST928LcFjErjCyt4bKz33i4kAYacx3emb8CcTNveH1u0yOHBAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9e89314166c84c1a4b8e5463a7a2675dd9a4e1cb2bfef1aa6a739429056839c0","last_reissued_at":"2026-05-20T11:54:46.553816Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T11:54:46.553816Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mobile-Agent-v3: Fundamental Agents for GUI Automation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Fei Huang, Feiyu Gao, Haiyang Xu, Haowei Liu, Jiabo Ye, Jingren Zhou, Jitong Liao, Junjie Cao, Junyang Wang, Ming Yan, Qi Zheng, Xi Zhang, Zhaoqing Zhu, Zhengxi Lu, Ziwei Zheng","submitted_at":"2025-08-21T00:39:12Z","abstract_excerpt":"This paper introduces GUI-Owl, a foundational GUI agent model that achieves state-of-the-art performance among open-source end-to-end models on ten GUI benchmarks across desktop and mobile environments, covering grounding, question answering, planning, decision-making, and procedural knowledge. GUI-Owl-7B achieves 66.4 on AndroidWorld and 29.4 on OSWorld. Building on this, we propose Mobile-Agent-v3, a general-purpose GUI agent framework that further improves performance to 73.3 on AndroidWorld and 37.7 on OSWorld, setting a new state-of-the-art for open-source GUI agent frameworks. GUI-Owl in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15144","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2508.15144/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2508.15144","created_at":"2026-05-20T11:54:46.553879+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.15144v2","created_at":"2026-05-20T11:54:46.553879+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15144","created_at":"2026-05-20T11:54:46.553879+00:00"},{"alias_kind":"pith_short_12","alias_value":"T2ETCQLGZBGB","created_at":"2026-05-20T11:54:46.553879+00:00"},{"alias_kind":"pith_short_16","alias_value":"T2ETCQLGZBGBUS4O","created_at":"2026-05-20T11:54:46.553879+00:00"},{"alias_kind":"pith_short_8","alias_value":"T2ETCQLG","created_at":"2026-05-20T11:54:46.553879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":23,"sample":[{"citing_arxiv_id":"2605.15556","citing_title":"TopoClaw: A Human-Centric and Topology-Aware Agent Operating System","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18048","citing_title":"DocOS: Towards Proactive Document-Guided Actions in GUI Agents","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2605.19260","citing_title":"AQuaUI: Visual Token Reduction for GUI Agents with Adaptive Quadtrees","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16883","citing_title":"SE-GA: Memory-Augmented Self-Evolution for GUI Agents","ref_index":48,"is_internal_anchor":true},{"citing_arxiv_id":"2509.07553","citing_title":"VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2510.24168","citing_title":"MGA: Memory-Driven GUI Agent for Observation-Centric Interaction","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2512.10371","citing_title":"AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2512.12634","citing_title":"MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2601.18842","citing_title":"GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents","ref_index":104,"is_internal_anchor":true},{"citing_arxiv_id":"2604.02345","citing_title":"UI-Oceanus: Scaling GUI Agents with Synthetic Environmental Dynamics","ref_index":50,"is_internal_anchor":true},{"citing_arxiv_id":"2604.09574","citing_title":"Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12481","citing_title":"ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08978","citing_title":"Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27955","citing_title":"GUI Agents with Reinforcement Learning: Toward Digital Inhabitants","ref_index":78,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08978","citing_title":"Learning to Explore: Scaling Agentic Reasoning via Exploration-Aware Policy Optimization","ref_index":23,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25380","citing_title":"Benchmarking and Improving GUI Agents in High-Dynamic Environments","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24348","citing_title":"OS-SPEAR: A Toolkit for the Safety, Performance,Efficiency, and Robustness Analysis of OS Agents","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22558","citing_title":"SOLAR-RL: Semi-Online Long-horizon Assignment Reinforcement Learning","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2605.01208","citing_title":"Faithful Mobile GUI Agents with Guided Advantage Estimator","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2604.11259","citing_title":"Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2604.25380","citing_title":"Benchmarking and Improving GUI Agents in High-Dynamic Environments","ref_index":47,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07831","citing_title":"Are GUI Agents Focused Enough? Automated Distraction via Semantic-level UI Element Injection","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17284","citing_title":"HalluClear: Diagnosing, Evaluating and Mitigating Hallucinations in GUI Agents","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T2ETCQLGZBGBUS4OKRR2PITHLX","json":"https://pith.science/pith/T2ETCQLGZBGBUS4OKRR2PITHLX.json","graph_json":"https://pith.science/api/pith-number/T2ETCQLGZBGBUS4OKRR2PITHLX/graph.json","events_json":"https://pith.science/api/pith-number/T2ETCQLGZBGBUS4OKRR2PITHLX/events.json","paper":"https://pith.science/paper/T2ETCQLG"},"agent_actions":{"view_html":"https://pith.science/pith/T2ETCQLGZBGBUS4OKRR2PITHLX","download_json":"https://pith.science/pith/T2ETCQLGZBGBUS4OKRR2PITHLX.json","view_paper":"https://pith.science/paper/T2ETCQLG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.15144&json=true","fetch_graph":"https://pith.science/api/pith-number/T2ETCQLGZBGBUS4OKRR2PITHLX/graph.json","fetch_events":"https://pith.science/api/pith-number/T2ETCQLGZBGBUS4OKRR2PITHLX/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T2ETCQLGZBGBUS4OKRR2PITHLX/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T2ETCQLGZBGBUS4OKRR2PITHLX/action/storage_attestation","attest_author":"https://pith.science/pith/T2ETCQLGZBGBUS4OKRR2PITHLX/action/author_attestation","sign_citation":"https://pith.science/pith/T2ETCQLGZBGBUS4OKRR2PITHLX/action/citation_signature","submit_replication":"https://pith.science/pith/T2ETCQLGZBGBUS4OKRR2PITHLX/action/replication_record"}},"created_at":"2026-05-20T11:54:46.553879+00:00","updated_at":"2026-05-20T11:54:46.553879+00:00"}