{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UIAOB4CTIJNMJZHEP2FS7VP5CV","short_pith_number":"pith:UIAOB4CT","schema_version":"1.0","canonical_sha256":"a200e0f053425ac4e4e47e8b2fd5fd1570e8d4c64ef8c42798bfdbeaf6ebee9d","source":{"kind":"arxiv","id":"2411.02006","version":3},"attestation_state":"computed","paper":{"title":"Foundations and Recent Trends in Multimodal Mobile Agents: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Biao Wu, Ling Chen, Meng Fang, Yanda Li, Yunchao Wei, Zhiwei Zhang","submitted_at":"2024-11-04T11:50:58Z","abstract_excerpt":"Mobile agents are essential for automating tasks in complex and dynamic mobile environments. As foundation models evolve, the demands for agents that can adapt in real-time and process multimodal data have grown. This survey provides a comprehensive review of mobile agent technologies, focusing on recent advancements that enhance real-time adaptability and multimodal interaction. Recent evaluation benchmarks have been developed better to capture the static and interactive environments of mobile tasks, offering more accurate assessments of agents' performance. We then categorize these advanceme"},"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":"2411.02006","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2024-11-04T11:50:58Z","cross_cats_sorted":[],"title_canon_sha256":"8376858831faa4666364caf165756e9a71f7eb7d670221bc6b99982746ba1cc4","abstract_canon_sha256":"f95dcedb0d6823fa9016e0fc2b0dd1a7a6b08dc7eb0935cccf9a268e81acd58f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:11:14.121048Z","signature_b64":"FALFANCdD28cETU6KO0XnOItAIIx+s80MWmn63O9UedOxy8bvACFcMujGMM203wmXfma/WbQyNz262JuLoY4Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a200e0f053425ac4e4e47e8b2fd5fd1570e8d4c64ef8c42798bfdbeaf6ebee9d","last_reissued_at":"2026-07-05T12:11:14.120488Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:11:14.120488Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Foundations and Recent Trends in Multimodal Mobile Agents: A Survey","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Biao Wu, Ling Chen, Meng Fang, Yanda Li, Yunchao Wei, Zhiwei Zhang","submitted_at":"2024-11-04T11:50:58Z","abstract_excerpt":"Mobile agents are essential for automating tasks in complex and dynamic mobile environments. As foundation models evolve, the demands for agents that can adapt in real-time and process multimodal data have grown. This survey provides a comprehensive review of mobile agent technologies, focusing on recent advancements that enhance real-time adaptability and multimodal interaction. Recent evaluation benchmarks have been developed better to capture the static and interactive environments of mobile tasks, offering more accurate assessments of agents' performance. We then categorize these advanceme"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.02006","kind":"arxiv","version":3},"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/2411.02006/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":"2411.02006","created_at":"2026-07-05T12:11:14.120549+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.02006v3","created_at":"2026-07-05T12:11:14.120549+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.02006","created_at":"2026-07-05T12:11:14.120549+00:00"},{"alias_kind":"pith_short_12","alias_value":"UIAOB4CTIJNM","created_at":"2026-07-05T12:11:14.120549+00:00"},{"alias_kind":"pith_short_16","alias_value":"UIAOB4CTIJNMJZHE","created_at":"2026-07-05T12:11:14.120549+00:00"},{"alias_kind":"pith_short_8","alias_value":"UIAOB4CT","created_at":"2026-07-05T12:11:14.120549+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.03804","citing_title":"ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2501.16150","citing_title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","ref_index":170,"is_internal_anchor":false},{"citing_arxiv_id":"2505.19662","citing_title":"FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2509.07553","citing_title":"VeriOS: Query-Driven Proactive Human-Agent-GUI Interaction for Trustworthy OS Agents","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2605.03804","citing_title":"ScrapMem: A Bio-inspired Framework for On-device Personalized Agent Memory via Optical Forgetting","ref_index":83,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09442","citing_title":"UIPress: Bringing Optical Token Compression to UI-to-Code Generation","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17817","citing_title":"Do LLMs Need to See Everything? A Benchmark and Study of Failures in LLM-driven Smartphone Automation using Screentext vs. Screenshots","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UIAOB4CTIJNMJZHEP2FS7VP5CV","json":"https://pith.science/pith/UIAOB4CTIJNMJZHEP2FS7VP5CV.json","graph_json":"https://pith.science/api/pith-number/UIAOB4CTIJNMJZHEP2FS7VP5CV/graph.json","events_json":"https://pith.science/api/pith-number/UIAOB4CTIJNMJZHEP2FS7VP5CV/events.json","paper":"https://pith.science/paper/UIAOB4CT"},"agent_actions":{"view_html":"https://pith.science/pith/UIAOB4CTIJNMJZHEP2FS7VP5CV","download_json":"https://pith.science/pith/UIAOB4CTIJNMJZHEP2FS7VP5CV.json","view_paper":"https://pith.science/paper/UIAOB4CT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.02006&json=true","fetch_graph":"https://pith.science/api/pith-number/UIAOB4CTIJNMJZHEP2FS7VP5CV/graph.json","fetch_events":"https://pith.science/api/pith-number/UIAOB4CTIJNMJZHEP2FS7VP5CV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UIAOB4CTIJNMJZHEP2FS7VP5CV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UIAOB4CTIJNMJZHEP2FS7VP5CV/action/storage_attestation","attest_author":"https://pith.science/pith/UIAOB4CTIJNMJZHEP2FS7VP5CV/action/author_attestation","sign_citation":"https://pith.science/pith/UIAOB4CTIJNMJZHEP2FS7VP5CV/action/citation_signature","submit_replication":"https://pith.science/pith/UIAOB4CTIJNMJZHEP2FS7VP5CV/action/replication_record"}},"created_at":"2026-07-05T12:11:14.120549+00:00","updated_at":"2026-07-05T12:11:14.120549+00:00"}