{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YCXNTIZ5UART7LNLGGE635UGYT","short_pith_number":"pith:YCXNTIZ5","schema_version":"1.0","canonical_sha256":"c0aed9a33da0233fadab3189edf686c4c9898772ec43426807b9eb05d076631d","source":{"kind":"arxiv","id":"2501.11733","version":2},"attestation_state":"computed","paper":{"title":"Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Fei Huang, Haiyang Xu, Heng Ji, Ji Zhang, Junyang Wang, Ming Yan, Xi Zhang, Zhenhailong Wang","submitted_at":"2025-01-20T20:35:46Z","abstract_excerpt":"Smartphones have become indispensable in modern life, yet navigating complex tasks on mobile devices often remains frustrating. Recent advancements in large multimodal model (LMM)-based mobile agents have demonstrated the ability to perceive and act in mobile environments. However, current approaches face significant limitations: they fall short in addressing real-world human needs, struggle with reasoning-intensive and long-horizon tasks, and lack mechanisms to learn and improve from prior experiences. To overcome these challenges, we introduce Mobile-Agent-E, a hierarchical multi-agent frame"},"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":"2501.11733","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-01-20T20:35:46Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"ce91aa07a0b9166a28137a58c7ba87b77a8c4a62a1050642d64e7966693a622d","abstract_canon_sha256":"9f04d6b322c14c5e69d142e128edad6b3760864c95f0f8b5f640ddc389bf0555"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:33.010914Z","signature_b64":"DEQ4jZrHENEiKLvO8VwFbGS4W1uzFOQjO/53h7pa7xcg2hYXJX0GZVVE6usnZZjmpMRiVULQOGFjb/2L0F7dDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c0aed9a33da0233fadab3189edf686c4c9898772ec43426807b9eb05d076631d","last_reissued_at":"2026-07-05T10:06:33.010472Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:33.010472Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mobile-Agent-E: Self-Evolving Mobile Assistant for Complex Tasks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Fei Huang, Haiyang Xu, Heng Ji, Ji Zhang, Junyang Wang, Ming Yan, Xi Zhang, Zhenhailong Wang","submitted_at":"2025-01-20T20:35:46Z","abstract_excerpt":"Smartphones have become indispensable in modern life, yet navigating complex tasks on mobile devices often remains frustrating. Recent advancements in large multimodal model (LMM)-based mobile agents have demonstrated the ability to perceive and act in mobile environments. However, current approaches face significant limitations: they fall short in addressing real-world human needs, struggle with reasoning-intensive and long-horizon tasks, and lack mechanisms to learn and improve from prior experiences. To overcome these challenges, we introduce Mobile-Agent-E, a hierarchical multi-agent frame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.11733","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/2501.11733/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":"2501.11733","created_at":"2026-07-05T10:06:33.010522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.11733v2","created_at":"2026-07-05T10:06:33.010522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.11733","created_at":"2026-07-05T10:06:33.010522+00:00"},{"alias_kind":"pith_short_12","alias_value":"YCXNTIZ5UART","created_at":"2026-07-05T10:06:33.010522+00:00"},{"alias_kind":"pith_short_16","alias_value":"YCXNTIZ5UART7LNL","created_at":"2026-07-05T10:06:33.010522+00:00"},{"alias_kind":"pith_short_8","alias_value":"YCXNTIZ5","created_at":"2026-07-05T10:06:33.010522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23049","citing_title":"PhoneBuddy: Training Open Models for Agentic Phone Use","ref_index":54,"is_internal_anchor":false},{"citing_arxiv_id":"2606.19926","citing_title":"MemGUI-Agent: An End-to-End Long-Horizon Mobile GUI Agent with Proactive Context Management","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31612","citing_title":"What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12666","citing_title":"CAPED: Context-Aware Privacy Exposure Defense for Mobile GUI Agents","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2606.09365","citing_title":"Experience Makes Skillful: Enabling Generalizable Medical Agent Reasoning via Self-Evolving Skill Memory","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2606.05513","citing_title":"EpiEvolve: Self-Evolving Agents for Streaming Pandemic Forecasting under Regime Shifts","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31612","citing_title":"What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States","ref_index":75,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28629","citing_title":"Mobile-Aptus: Confidence-Driven Proactive and Robust Interaction in MLLM-based Mobile-Using Agents","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2606.06840","citing_title":"Characterize Then Distill: Mechanistic Reasoning in Large Output Spaces","ref_index":112,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10347","citing_title":"How Mobile World Model Guides GUI Agents?","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17406","citing_title":"Rethinking Side-Channel Analysis: Automated Discovery and Analysis of Side-Channel Leakage with LLM-Assisted Agents","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2506.12382","citing_title":"Exploring the Secondary Risks of Large Language Models","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2506.20332","citing_title":"Mobile-R1: Towards Interactive Capability for VLM-Based Mobile Agent via Systematic Training","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2508.19679","citing_title":"InquireMobile: Teaching VLM-based Mobile Agent to Request Human Assistance via Reinforcement Fine-Tuning","ref_index":20,"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":33,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21982","citing_title":"RISK: A Framework for GUI Agents in E-commerce Risk Management","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2512.12634","citing_title":"MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2602.21858","citing_title":"ProactiveMobile: A Comprehensive Benchmark for Boosting Proactive Intelligence on Mobile Devices","ref_index":39,"is_internal_anchor":false},{"citing_arxiv_id":"2507.21046","citing_title":"A Survey of Self-Evolving Agents: What, When, How, and Where to Evolve on the Path to Artificial Super Intelligence","ref_index":166,"is_internal_anchor":false},{"citing_arxiv_id":"2604.00458","citing_title":"LDMDroid: Leveraging LLMs for Detecting Data Manipulation Errors in Android Apps","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":43,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10347","citing_title":"How Mobile World Model Guides GUI Agents?","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13531","citing_title":"RiskWebWorld: A Realistic Interactive Benchmark for GUI Agents in E-commerce Risk Management","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YCXNTIZ5UART7LNLGGE635UGYT","json":"https://pith.science/pith/YCXNTIZ5UART7LNLGGE635UGYT.json","graph_json":"https://pith.science/api/pith-number/YCXNTIZ5UART7LNLGGE635UGYT/graph.json","events_json":"https://pith.science/api/pith-number/YCXNTIZ5UART7LNLGGE635UGYT/events.json","paper":"https://pith.science/paper/YCXNTIZ5"},"agent_actions":{"view_html":"https://pith.science/pith/YCXNTIZ5UART7LNLGGE635UGYT","download_json":"https://pith.science/pith/YCXNTIZ5UART7LNLGGE635UGYT.json","view_paper":"https://pith.science/paper/YCXNTIZ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.11733&json=true","fetch_graph":"https://pith.science/api/pith-number/YCXNTIZ5UART7LNLGGE635UGYT/graph.json","fetch_events":"https://pith.science/api/pith-number/YCXNTIZ5UART7LNLGGE635UGYT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YCXNTIZ5UART7LNLGGE635UGYT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YCXNTIZ5UART7LNLGGE635UGYT/action/storage_attestation","attest_author":"https://pith.science/pith/YCXNTIZ5UART7LNLGGE635UGYT/action/author_attestation","sign_citation":"https://pith.science/pith/YCXNTIZ5UART7LNLGGE635UGYT/action/citation_signature","submit_replication":"https://pith.science/pith/YCXNTIZ5UART7LNLGGE635UGYT/action/replication_record"}},"created_at":"2026-07-05T10:06:33.010522+00:00","updated_at":"2026-07-05T10:06:33.010522+00:00"}