{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NGK5Q7C6WVSIK2VU7SHT3E4TOI","short_pith_number":"pith:NGK5Q7C6","schema_version":"1.0","canonical_sha256":"6995d87c5eb564856ab4fc8f3d939372073f635f49256bda308e70a25cb9d394","source":{"kind":"arxiv","id":"2503.02268","version":3},"attestation_state":"computed","paper":{"title":"AppAgentX: Evolving GUI Agents as Proficient Smartphone Users","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenxi Song, Chi Zhang, Joey Tianyi Zhou, Wenjia Jiang, Xu Yang, Yangyang Zhuang","submitted_at":"2025-03-04T04:34:09Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have led to the development of intelligent LLM-based agents capable of interacting with graphical user interfaces (GUIs). These agents demonstrate strong reasoning and adaptability, enabling them to perform complex tasks that traditionally required predefined rules. However, the reliance on step-by-step reasoning in LLM-based agents often results in inefficiencies, particularly for routine tasks. In contrast, traditional rule-based systems excel in efficiency but lack the intelligence and flexibility to adapt to novel scenarios. To address th"},"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":"2503.02268","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-03-04T04:34:09Z","cross_cats_sorted":[],"title_canon_sha256":"5addabff3087bb454834fb8d7beeff0c3705a661069ec192819a88f011a2b546","abstract_canon_sha256":"efc519c6d76899ae319d2a79f179a4cc46ef1c81af10eb12497b3ccc10b23cb7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:14.461624Z","signature_b64":"kdiCii9YONakOcg+lrAIrXj8CXNprKf7gGRS2OV6KHg4TF46zLNu3cNXOlEY0CpYUfGMVGEVKAzRnTTfbQCoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6995d87c5eb564856ab4fc8f3d939372073f635f49256bda308e70a25cb9d394","last_reissued_at":"2026-07-05T10:49:14.461160Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:14.461160Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"AppAgentX: Evolving GUI Agents as Proficient Smartphone Users","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenxi Song, Chi Zhang, Joey Tianyi Zhou, Wenjia Jiang, Xu Yang, Yangyang Zhuang","submitted_at":"2025-03-04T04:34:09Z","abstract_excerpt":"Recent advancements in Large Language Models (LLMs) have led to the development of intelligent LLM-based agents capable of interacting with graphical user interfaces (GUIs). These agents demonstrate strong reasoning and adaptability, enabling them to perform complex tasks that traditionally required predefined rules. However, the reliance on step-by-step reasoning in LLM-based agents often results in inefficiencies, particularly for routine tasks. In contrast, traditional rule-based systems excel in efficiency but lack the intelligence and flexibility to adapt to novel scenarios. To address th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.02268","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/2503.02268/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":"2503.02268","created_at":"2026-07-05T10:49:14.461214+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.02268v3","created_at":"2026-07-05T10:49:14.461214+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.02268","created_at":"2026-07-05T10:49:14.461214+00:00"},{"alias_kind":"pith_short_12","alias_value":"NGK5Q7C6WVSI","created_at":"2026-07-05T10:49:14.461214+00:00"},{"alias_kind":"pith_short_16","alias_value":"NGK5Q7C6WVSIK2VU","created_at":"2026-07-05T10:49:14.461214+00:00"},{"alias_kind":"pith_short_8","alias_value":"NGK5Q7C6","created_at":"2026-07-05T10:49:14.461214+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.00333","citing_title":"(A)I Sees What You Don't: Exploiting New Attack Surfaces in Third-Party Mobile Agents","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18652","citing_title":"MementoGUI: Learning Agentic Multimodal Memory Control for Long-Horizon GUI Agents","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":266,"is_internal_anchor":false},{"citing_arxiv_id":"2506.19500","citing_title":"NaviAgent: Bilevel Planning on Tool Navigation Graph for Large-Scale Orchestration","ref_index":13,"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":13,"is_internal_anchor":false},{"citing_arxiv_id":"2509.21982","citing_title":"RISK: A Framework for GUI Agents in E-commerce Risk Management","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11259","citing_title":"Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07110","citing_title":"Securing Computer-Use Agents: A Unified Architecture-Lifecycle Framework for Deployment-Grounded Reliability","ref_index":68,"is_internal_anchor":false},{"citing_arxiv_id":"2604.14113","citing_title":"UI-Zoomer: Uncertainty-Driven Adaptive Zoom-In for GUI Grounding","ref_index":10,"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":18,"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":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NGK5Q7C6WVSIK2VU7SHT3E4TOI","json":"https://pith.science/pith/NGK5Q7C6WVSIK2VU7SHT3E4TOI.json","graph_json":"https://pith.science/api/pith-number/NGK5Q7C6WVSIK2VU7SHT3E4TOI/graph.json","events_json":"https://pith.science/api/pith-number/NGK5Q7C6WVSIK2VU7SHT3E4TOI/events.json","paper":"https://pith.science/paper/NGK5Q7C6"},"agent_actions":{"view_html":"https://pith.science/pith/NGK5Q7C6WVSIK2VU7SHT3E4TOI","download_json":"https://pith.science/pith/NGK5Q7C6WVSIK2VU7SHT3E4TOI.json","view_paper":"https://pith.science/paper/NGK5Q7C6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.02268&json=true","fetch_graph":"https://pith.science/api/pith-number/NGK5Q7C6WVSIK2VU7SHT3E4TOI/graph.json","fetch_events":"https://pith.science/api/pith-number/NGK5Q7C6WVSIK2VU7SHT3E4TOI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NGK5Q7C6WVSIK2VU7SHT3E4TOI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NGK5Q7C6WVSIK2VU7SHT3E4TOI/action/storage_attestation","attest_author":"https://pith.science/pith/NGK5Q7C6WVSIK2VU7SHT3E4TOI/action/author_attestation","sign_citation":"https://pith.science/pith/NGK5Q7C6WVSIK2VU7SHT3E4TOI/action/citation_signature","submit_replication":"https://pith.science/pith/NGK5Q7C6WVSIK2VU7SHT3E4TOI/action/replication_record"}},"created_at":"2026-07-05T10:49:14.461214+00:00","updated_at":"2026-07-05T10:49:14.461214+00:00"}