{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:OWKBSHYR6VWOOP37B7MLWM7XOO","short_pith_number":"pith:OWKBSHYR","schema_version":"1.0","canonical_sha256":"7594191f11f56ce73f7f0fd8bb33f773a7214c90547980497aba691e2297b1d5","source":{"kind":"arxiv","id":"2406.01014","version":1},"attestation_state":"computed","paper":{"title":"Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Fei Huang, Haitao Jia, Haiyang Xu, Jitao Sang, Ji Zhang, Junyang Wang, Ming Yan, Weizhou Shen, Xi Zhang","submitted_at":"2024-06-03T05:50:00Z","abstract_excerpt":"Mobile device operation tasks are increasingly becoming a popular multi-modal AI application scenario. Current Multi-modal Large Language Models (MLLMs), constrained by their training data, lack the capability to function effectively as operation assistants. Instead, MLLM-based agents, which enhance capabilities through tool invocation, are gradually being applied to this scenario. However, the two major navigation challenges in mobile device operation tasks, task progress navigation and focus content navigation, are significantly complicated under the single-agent architecture of existing wor"},"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":"2406.01014","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-06-03T05:50:00Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"dc77e70dfe7c270ca26034176787b80c23be9ae755f4ff327c6e817a93945a24","abstract_canon_sha256":"abd79317caae5da89ecf2f5487246ce9d18edb98175a3da87ef1d23943f35771"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:33.832698Z","signature_b64":"HTFKNn3XkzX+E8bZQFycM7q6ZVJqRy2vvFoYlVgvZCqX3rmuupLhNHpjhvWPji76l4rkzLsuGi9K1yRno0d0BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7594191f11f56ce73f7f0fd8bb33f773a7214c90547980497aba691e2297b1d5","last_reissued_at":"2026-07-05T08:26:33.832190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:33.832190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mobile-Agent-v2: Mobile Device Operation Assistant with Effective Navigation via Multi-Agent Collaboration","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Fei Huang, Haitao Jia, Haiyang Xu, Jitao Sang, Ji Zhang, Junyang Wang, Ming Yan, Weizhou Shen, Xi Zhang","submitted_at":"2024-06-03T05:50:00Z","abstract_excerpt":"Mobile device operation tasks are increasingly becoming a popular multi-modal AI application scenario. Current Multi-modal Large Language Models (MLLMs), constrained by their training data, lack the capability to function effectively as operation assistants. Instead, MLLM-based agents, which enhance capabilities through tool invocation, are gradually being applied to this scenario. However, the two major navigation challenges in mobile device operation tasks, task progress navigation and focus content navigation, are significantly complicated under the single-agent architecture of existing wor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.01014","kind":"arxiv","version":1},"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/2406.01014/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":"2406.01014","created_at":"2026-07-05T08:26:33.832247+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.01014v1","created_at":"2026-07-05T08:26:33.832247+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.01014","created_at":"2026-07-05T08:26:33.832247+00:00"},{"alias_kind":"pith_short_12","alias_value":"OWKBSHYR6VWO","created_at":"2026-07-05T08:26:33.832247+00:00"},{"alias_kind":"pith_short_16","alias_value":"OWKBSHYR6VWOOP37","created_at":"2026-07-05T08:26:33.832247+00:00"},{"alias_kind":"pith_short_8","alias_value":"OWKBSHYR","created_at":"2026-07-05T08:26:33.832247+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23049","citing_title":"PhoneBuddy: Training Open Models for Agentic Phone Use","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2505.03364","citing_title":"DroidRetriever: A Transparent and Steerable Automation System for Collaborative Mobile Information Seeking","ref_index":58,"is_internal_anchor":false},{"citing_arxiv_id":"2408.04840","citing_title":"mPLUG-Owl3: Towards Long Image-Sequence Understanding in Multi-Modal Large Language Models","ref_index":249,"is_internal_anchor":false},{"citing_arxiv_id":"2506.17697","citing_title":"Beyond Syntax: Action Semantics Learning for App Agents","ref_index":7,"is_internal_anchor":false},{"citing_arxiv_id":"2509.06477","citing_title":"MAS-Bench: A Unified Benchmark for Shortcut-Augmented Hybrid Mobile GUI Agents","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2512.06721","citing_title":"ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild","ref_index":49,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12481","citing_title":"ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13463","citing_title":"From Exploration to Specification: LLM-Based Property Generation for Mobile App Testing","ref_index":66,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14113","citing_title":"UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OWKBSHYR6VWOOP37B7MLWM7XOO","json":"https://pith.science/pith/OWKBSHYR6VWOOP37B7MLWM7XOO.json","graph_json":"https://pith.science/api/pith-number/OWKBSHYR6VWOOP37B7MLWM7XOO/graph.json","events_json":"https://pith.science/api/pith-number/OWKBSHYR6VWOOP37B7MLWM7XOO/events.json","paper":"https://pith.science/paper/OWKBSHYR"},"agent_actions":{"view_html":"https://pith.science/pith/OWKBSHYR6VWOOP37B7MLWM7XOO","download_json":"https://pith.science/pith/OWKBSHYR6VWOOP37B7MLWM7XOO.json","view_paper":"https://pith.science/paper/OWKBSHYR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.01014&json=true","fetch_graph":"https://pith.science/api/pith-number/OWKBSHYR6VWOOP37B7MLWM7XOO/graph.json","fetch_events":"https://pith.science/api/pith-number/OWKBSHYR6VWOOP37B7MLWM7XOO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OWKBSHYR6VWOOP37B7MLWM7XOO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OWKBSHYR6VWOOP37B7MLWM7XOO/action/storage_attestation","attest_author":"https://pith.science/pith/OWKBSHYR6VWOOP37B7MLWM7XOO/action/author_attestation","sign_citation":"https://pith.science/pith/OWKBSHYR6VWOOP37B7MLWM7XOO/action/citation_signature","submit_replication":"https://pith.science/pith/OWKBSHYR6VWOOP37B7MLWM7XOO/action/replication_record"}},"created_at":"2026-07-05T08:26:33.832247+00:00","updated_at":"2026-07-05T08:26:33.832247+00:00"}