{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VY54IEHHHVKTMMRY4ZKPW4PDPV","short_pith_number":"pith:VY54IEHH","schema_version":"1.0","canonical_sha256":"ae3bc410e73d55363238e654fb71e37d413a7235e636c9a542a995e47a566903","source":{"kind":"arxiv","id":"2504.13865","version":2},"attestation_state":"computed","paper":{"title":"A Survey on (M)LLM-Based GUI Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.HC","authors_text":"Fei Tang, Guiyang Hou, Hang Zhang, Haolei Xu, Jian Shao, Jun Xiao, Kaitao Song, Siqi Chen, Weiming Lu, Wenqi Zhang, Xingyu Wu, Yongliang Shen, Yuchen Yan, Yueting Zhuang, Zeqi Tan","submitted_at":"2025-03-27T17:58:31Z","abstract_excerpt":"Graphical User Interface (GUI) Agents have emerged as a transformative paradigm in human-computer interaction, evolving from rule-based automation scripts to sophisticated AI-driven systems capable of understanding and executing complex interface operations. This survey provides a comprehensive examination of the rapidly advancing field of LLM-based GUI Agents, systematically analyzing their architectural foundations, technical components, and evaluation methodologies. We identify and analyze four fundamental components that constitute modern GUI Agents: (1) perception systems that integrate t"},"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":"2504.13865","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.HC","submitted_at":"2025-03-27T17:58:31Z","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"title_canon_sha256":"02c9ccc1d0e1f2fb85c9f8114f2879f48721674913b210afeded8d8b061d715f","abstract_canon_sha256":"a4215df24b8aff40753b3c52edc05fec23af60468bcb55037f34b24bd7927eb6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:46.070378Z","signature_b64":"U82GNYA8nNFsLC9KGio2hjf2oGtbp9rKB0tbjeP6xeXVaQvGHDG9GjhXg9r1Diya8WyBP4BUAA9PAAdlWWNoDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ae3bc410e73d55363238e654fb71e37d413a7235e636c9a542a995e47a566903","last_reissued_at":"2026-07-05T11:15:46.069879Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:46.069879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on (M)LLM-Based GUI Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.CV"],"primary_cat":"cs.HC","authors_text":"Fei Tang, Guiyang Hou, Hang Zhang, Haolei Xu, Jian Shao, Jun Xiao, Kaitao Song, Siqi Chen, Weiming Lu, Wenqi Zhang, Xingyu Wu, Yongliang Shen, Yuchen Yan, Yueting Zhuang, Zeqi Tan","submitted_at":"2025-03-27T17:58:31Z","abstract_excerpt":"Graphical User Interface (GUI) Agents have emerged as a transformative paradigm in human-computer interaction, evolving from rule-based automation scripts to sophisticated AI-driven systems capable of understanding and executing complex interface operations. This survey provides a comprehensive examination of the rapidly advancing field of LLM-based GUI Agents, systematically analyzing their architectural foundations, technical components, and evaluation methodologies. We identify and analyze four fundamental components that constitute modern GUI Agents: (1) perception systems that integrate t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.13865","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/2504.13865/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":"2504.13865","created_at":"2026-07-05T11:15:46.069935+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.13865v2","created_at":"2026-07-05T11:15:46.069935+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.13865","created_at":"2026-07-05T11:15:46.069935+00:00"},{"alias_kind":"pith_short_12","alias_value":"VY54IEHHHVKT","created_at":"2026-07-05T11:15:46.069935+00:00"},{"alias_kind":"pith_short_16","alias_value":"VY54IEHHHVKTMMRY","created_at":"2026-07-05T11:15:46.069935+00:00"},{"alias_kind":"pith_short_8","alias_value":"VY54IEHH","created_at":"2026-07-05T11:15:46.069935+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":11,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.27330","citing_title":"Empowering GUI Agents via Autonomous Experience Exploration and Hindsight Experience Utilization for Task Planning","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10522","citing_title":"GUI-AC: Enhancing Continual Learning in GUI Agents","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28534","citing_title":"GUI-CIDER: Mid-training GUI Agents via Causal Internalization and Density-aware Exemplar Reselection","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2507.10610","citing_title":"LaSM: Layer-wise Scaling Mechanism for Defending Pop-up Attack on GUI Agents","ref_index":17,"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":28,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12549","citing_title":"What Happens Before Decoding? Prefill Determines GUI Grounding in VLMs","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2509.02544","citing_title":"UI-TARS-2 Technical Report: Advancing GUI Agent with Multi-Turn Reinforcement Learning","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11259","citing_title":"Mobile GUI Agent Privacy Personalization with Trajectory Induced Preference Optimization","ref_index":31,"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":23,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13488","citing_title":"Towards Scalable Lightweight GUI Agents via Multi-role Orchestration","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VY54IEHHHVKTMMRY4ZKPW4PDPV","json":"https://pith.science/pith/VY54IEHHHVKTMMRY4ZKPW4PDPV.json","graph_json":"https://pith.science/api/pith-number/VY54IEHHHVKTMMRY4ZKPW4PDPV/graph.json","events_json":"https://pith.science/api/pith-number/VY54IEHHHVKTMMRY4ZKPW4PDPV/events.json","paper":"https://pith.science/paper/VY54IEHH"},"agent_actions":{"view_html":"https://pith.science/pith/VY54IEHHHVKTMMRY4ZKPW4PDPV","download_json":"https://pith.science/pith/VY54IEHHHVKTMMRY4ZKPW4PDPV.json","view_paper":"https://pith.science/paper/VY54IEHH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.13865&json=true","fetch_graph":"https://pith.science/api/pith-number/VY54IEHHHVKTMMRY4ZKPW4PDPV/graph.json","fetch_events":"https://pith.science/api/pith-number/VY54IEHHHVKTMMRY4ZKPW4PDPV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VY54IEHHHVKTMMRY4ZKPW4PDPV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VY54IEHHHVKTMMRY4ZKPW4PDPV/action/storage_attestation","attest_author":"https://pith.science/pith/VY54IEHHHVKTMMRY4ZKPW4PDPV/action/author_attestation","sign_citation":"https://pith.science/pith/VY54IEHHHVKTMMRY4ZKPW4PDPV/action/citation_signature","submit_replication":"https://pith.science/pith/VY54IEHHHVKTMMRY4ZKPW4PDPV/action/replication_record"}},"created_at":"2026-07-05T11:15:46.069935+00:00","updated_at":"2026-07-05T11:15:46.069935+00:00"}