{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:NLIXKHKPME3NHIOJQ4YVW5FPMV","short_pith_number":"pith:NLIXKHKP","schema_version":"1.0","canonical_sha256":"6ad1751d4f6136d3a1c987315b74af6554e2880aa8cf1bc0bf625382143509aa","source":{"kind":"arxiv","id":"2312.13771","version":2},"attestation_state":"computed","paper":{"title":"AppAgent: Multimodal Agents as Smartphone Users","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Fu, Chi Zhang, Gang Yu, Jiaxuan Liu, Xin Chen, Yucheng Han, Zebiao Huang, Zhao Yang","submitted_at":"2023-12-21T11:52:45Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have led to the creation of intelligent agents capable of performing complex tasks. This paper introduces a novel LLM-based multimodal agent framework designed to operate smartphone applications. Our framework enables the agent to operate smartphone applications through a simplified action space, mimicking human-like interactions such as tapping and swiping. This novel approach bypasses the need for system back-end access, thereby broadening its applicability across diverse apps. Central to our agent's functionality is its innovative learning"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2312.13771","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-12-21T11:52:45Z","cross_cats_sorted":[],"title_canon_sha256":"4af3c8c63187b7042d09f7707a621ba4ff661c5067efaa5e0c6ce20838930e23","abstract_canon_sha256":"9a32a980081b8d77ebaf7885933ae6cda5952055956415891cc187a99082d678"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.406386Z","signature_b64":"QGz84h7qlYfPuGlhpfUtNkid7k19mSKKZxx856DGBeG7kSEVLP1dURPiV7pCzHK7AnTBZjYSAARImJqxvGh6Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ad1751d4f6136d3a1c987315b74af6554e2880aa8cf1bc0bf625382143509aa","last_reissued_at":"2026-05-17T23:38:14.405660Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.405660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AppAgent: Multimodal Agents as Smartphone Users","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations.","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Fu, Chi Zhang, Gang Yu, Jiaxuan Liu, Xin Chen, Yucheng Han, Zebiao Huang, Zhao Yang","submitted_at":"2023-12-21T11:52:45Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have led to the creation of intelligent agents capable of performing complex tasks. This paper introduces a novel LLM-based multimodal agent framework designed to operate smartphone applications. Our framework enables the agent to operate smartphone applications through a simplified action space, mimicking human-like interactions such as tapping and swiping. This novel approach bypasses the need for system back-end access, thereby broadening its applicability across diverse apps. Central to our agent's functionality is its innovative learning"},"claims":{"count":3,"items":[{"kind":"strongest_claim","text":"Our framework enables the agent to operate smartphone applications through a simplified action space, mimicking human-like interactions such as tapping and swiping. This novel approach bypasses the need for system back-end access, thereby broadening its applicability across diverse apps.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The agent can reliably learn to navigate and execute tasks in new apps through autonomous exploration or human demonstrations, producing a knowledge base that generalizes across applications.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"}],"snapshot_sha256":"e0d601a309ea2d10bf0cc1852192cc740bdfac984662b4a09ca1aa64d75b0176"},"source":{"id":"2312.13771","kind":"arxiv","version":2},"verdict":{"id":"8c086a79-6616-4ce5-893d-c4daba15993a","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T10:10:48.536796Z","strongest_claim":"Our framework enables the agent to operate smartphone applications through a simplified action space, mimicking human-like interactions such as tapping and swiping. This novel approach bypasses the need for system back-end access, thereby broadening its applicability across diverse apps.","one_line_summary":"AppAgent lets large language models operate diverse smartphone apps via visual interactions and learns app usage from exploration or demonstrations.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The agent can reliably learn to navigate and execute tasks in new apps through autonomous exploration or human demonstrations, producing a knowledge base that generalizes across applications.","pith_extraction_headline":""},"references":{"count":286,"sample":[{"doi":"","year":2022,"title":"Meta FAIR, Anton Bakhtin, Noam Brown, Emily Dinan, Gabriele Farina, Colin Flaherty, Daniel Fried, Andrew Goff, Jonathan Gray, Hengyuan Hu, et al. 2022. Human-level play in the game of diplomacy by com","work_id":"1ceb4a39-65c8-410c-9767-2ac7b120f2e8","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"Multimodal web navigation with instruction-finetuned foundation models","work_id":"0f8b8630-9215-4cb8-9b7d-e58e6b1f7bbb","ref_index":6,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"A Real-World WebAgent with Planning, Long Context Understanding, and Program Synthesis","work_id":"0915d1fc-bc46-4128-871e-f9233dca44b6","ref_index":7,"cited_arxiv_id":"2307.12856","is_internal_anchor":true},{"doi":"","year":2023,"title":"Chartllama: A multimodal llm for chart understanding and generation","work_id":"f6c4f1ff-0ce7-47e8-82e5-5c24c2a3ed9f","ref_index":8,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework","work_id":"891b9780-a800-4e3c-bba0-53597ab8dc98","ref_index":9,"cited_arxiv_id":"2308.00352","is_internal_anchor":true}],"resolved_work":286,"snapshot_sha256":"885821595754b102708f214ad9e2814c5947fa18007c701fd0328ce61111a172","internal_anchors":19},"formal_canon":{"evidence_count":2,"snapshot_sha256":"f5de55fee7c9bea80b8fbbb1c74c2316415b5a18f619b190dd3414e0f92b7942"},"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":"2312.13771","created_at":"2026-05-17T23:38:14.405794+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.13771v2","created_at":"2026-05-17T23:38:14.405794+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.13771","created_at":"2026-05-17T23:38:14.405794+00:00"},{"alias_kind":"pith_short_12","alias_value":"NLIXKHKPME3N","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"NLIXKHKPME3NHIOJ","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"NLIXKHKP","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":27,"internal_anchor_count":27,"sample":[{"citing_arxiv_id":"2501.16150","citing_title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","ref_index":184,"is_internal_anchor":true},{"citing_arxiv_id":"2503.14075","citing_title":"Growing a Multi-head Twig via Distillation and Reinforcement Learning to Accelerate Large Vision-Language Models","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2505.03364","citing_title":"DroidRetriever: A Transparent and Steerable Automation System for Collaborative Mobile Information Seeking","ref_index":68,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05765","citing_title":"X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07358","citing_title":"A Comprehensive Survey on Agent Skills: Taxonomy, Techniques, and Applications","ref_index":80,"is_internal_anchor":true},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":18,"is_internal_anchor":true},{"citing_arxiv_id":"2504.14239","citing_title":"InfiGUI-R1: Advancing Multimodal GUI Agents from Reactive Actors to Deliberative Reasoners","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2412.04454","citing_title":"Aguvis: Unified Pure Vision Agents for Autonomous GUI Interaction","ref_index":117,"is_internal_anchor":true},{"citing_arxiv_id":"2503.09572","citing_title":"Plan-and-Act: Improving Planning of Agents for Long-Horizon Tasks","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2401.10935","citing_title":"SeeClick: Harnessing GUI Grounding for Advanced Visual GUI Agents","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2512.06721","citing_title":"ProAgent: Harnessing On-Demand Sensory Contexts for Proactive LLM Agent Systems in the Wild","ref_index":65,"is_internal_anchor":true},{"citing_arxiv_id":"2401.16158","citing_title":"Mobile-Agent: Autonomous Multi-Modal Mobile Device Agent with Visual Perception","ref_index":12,"is_internal_anchor":true},{"citing_arxiv_id":"2512.10371","citing_title":"AgentProg: Empowering Long-Horizon GUI Agents with Program-Guided Context Management","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2601.18842","citing_title":"GUIGuard-Bench: Toward a General Evaluation for Privacy-Preserving GUI Agents","ref_index":40,"is_internal_anchor":true},{"citing_arxiv_id":"2503.21620","citing_title":"UI-R1: Enhancing Efficient Action Prediction of GUI Agents by Reinforcement Learning","ref_index":17,"is_internal_anchor":true},{"citing_arxiv_id":"2306.13549","citing_title":"A Survey on Multimodal Large Language Models","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2308.11432","citing_title":"A Survey on Large Language Model based Autonomous Agents","ref_index":95,"is_internal_anchor":true},{"citing_arxiv_id":"2602.20867","citing_title":"SoK: Agentic Skills -- Beyond Tool Use in LLM Agents","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2410.23218","citing_title":"OS-ATLAS: A Foundation Action Model for Generalist GUI Agents","ref_index":90,"is_internal_anchor":true},{"citing_arxiv_id":"2604.26622","citing_title":"OCR-Memory: Optical Context Retrieval for Long-Horizon Agent Memory","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2604.24441","citing_title":"AutoGUI-v2: A Comprehensive Multi-Modal GUI Functionality Understanding Benchmark","ref_index":63,"is_internal_anchor":true},{"citing_arxiv_id":"2605.05765","citing_title":"X-OmniClaw Technical Report: A Unified Mobile Agent for Multimodal Understanding and Interaction","ref_index":5,"is_internal_anchor":true},{"citing_arxiv_id":"2604.18860","citing_title":"Temporal UI State Inconsistency in Desktop GUI Agents: Formalizing and Defending Against TOCTOU Attacks on Computer-Use Agents","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV","json":"https://pith.science/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV.json","graph_json":"https://pith.science/api/pith-number/NLIXKHKPME3NHIOJQ4YVW5FPMV/graph.json","events_json":"https://pith.science/api/pith-number/NLIXKHKPME3NHIOJQ4YVW5FPMV/events.json","paper":"https://pith.science/paper/NLIXKHKP"},"agent_actions":{"view_html":"https://pith.science/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV","download_json":"https://pith.science/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV.json","view_paper":"https://pith.science/paper/NLIXKHKP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.13771&json=true","fetch_graph":"https://pith.science/api/pith-number/NLIXKHKPME3NHIOJQ4YVW5FPMV/graph.json","fetch_events":"https://pith.science/api/pith-number/NLIXKHKPME3NHIOJQ4YVW5FPMV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV/action/storage_attestation","attest_author":"https://pith.science/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV/action/author_attestation","sign_citation":"https://pith.science/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV/action/citation_signature","submit_replication":"https://pith.science/pith/NLIXKHKPME3NHIOJQ4YVW5FPMV/action/replication_record"}},"created_at":"2026-05-17T23:38:14.405794+00:00","updated_at":"2026-05-17T23:38:14.405794+00:00"}