{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:KLXVG5R444CQYIRGBG2WA7X73Y","short_pith_number":"pith:KLXVG5R4","schema_version":"1.0","canonical_sha256":"52ef53763ce7050c222609b5607effde1e0f6bc1c1ec1e0764f47b78b77839ed","source":{"kind":"arxiv","id":"2402.11941","version":3},"attestation_state":"computed","paper":{"title":"CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Xinbei Ma, Zhuosheng Zhang","submitted_at":"2024-02-19T08:29:03Z","abstract_excerpt":"Multimodal large language models (MLLMs) have shown remarkable potential as human-like autonomous language agents to interact with real-world environments, especially for graphical user interface (GUI) automation. However, those GUI agents require comprehensive cognition ability including exhaustive perception and reliable action response. We propose a Comprehensive Cognitive LLM Agent, CoCo-Agent, with two novel approaches, comprehensive environment perception (CEP) and conditional action prediction (CAP), to systematically improve the GUI automation performance. First, CEP facilitates the GU"},"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":"2402.11941","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T08:29:03Z","cross_cats_sorted":[],"title_canon_sha256":"fba7e2422e92a197c8550ba8d257596b8329bfbc981ec5e4062c997bb20684fa","abstract_canon_sha256":"0318b160e55d851c78c10ee559d503a59ff8414dba78cbf1e2d376f51d4a2851"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:26:20.022468Z","signature_b64":"Y1sBBZJkeuyjj13PAVdGDw4ga8927vd2y5Wlpt0Yb+Ny5ICqu/LJ19GzysC7o93F9+btTfsK7cXoUzHpmg5KBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"52ef53763ce7050c222609b5607effde1e0f6bc1c1ec1e0764f47b78b77839ed","last_reissued_at":"2026-07-05T08:26:20.021900Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:26:20.021900Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoCo-Agent: A Comprehensive Cognitive MLLM Agent for Smartphone GUI Automation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hai Zhao, Xinbei Ma, Zhuosheng Zhang","submitted_at":"2024-02-19T08:29:03Z","abstract_excerpt":"Multimodal large language models (MLLMs) have shown remarkable potential as human-like autonomous language agents to interact with real-world environments, especially for graphical user interface (GUI) automation. However, those GUI agents require comprehensive cognition ability including exhaustive perception and reliable action response. We propose a Comprehensive Cognitive LLM Agent, CoCo-Agent, with two novel approaches, comprehensive environment perception (CEP) and conditional action prediction (CAP), to systematically improve the GUI automation performance. First, CEP facilitates the GU"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.11941","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/2402.11941/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":"2402.11941","created_at":"2026-07-05T08:26:20.022070+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.11941v3","created_at":"2026-07-05T08:26:20.022070+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.11941","created_at":"2026-07-05T08:26:20.022070+00:00"},{"alias_kind":"pith_short_12","alias_value":"KLXVG5R444CQ","created_at":"2026-07-05T08:26:20.022070+00:00"},{"alias_kind":"pith_short_16","alias_value":"KLXVG5R444CQYIRG","created_at":"2026-07-05T08:26:20.022070+00:00"},{"alias_kind":"pith_short_8","alias_value":"KLXVG5R4","created_at":"2026-07-05T08:26:20.022070+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.12634","citing_title":"MobiBench: Multi-Branch, Modular Benchmark for Mobile GUI Agents","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09574","citing_title":"Turing Test on Screen: A Benchmark for Mobile GUI Agent Humanization","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20279","citing_title":"AgentLens: Adaptive Visual Modalities for Human-Agent Interaction in Mobile GUI Agents","ref_index":32,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KLXVG5R444CQYIRGBG2WA7X73Y","json":"https://pith.science/pith/KLXVG5R444CQYIRGBG2WA7X73Y.json","graph_json":"https://pith.science/api/pith-number/KLXVG5R444CQYIRGBG2WA7X73Y/graph.json","events_json":"https://pith.science/api/pith-number/KLXVG5R444CQYIRGBG2WA7X73Y/events.json","paper":"https://pith.science/paper/KLXVG5R4"},"agent_actions":{"view_html":"https://pith.science/pith/KLXVG5R444CQYIRGBG2WA7X73Y","download_json":"https://pith.science/pith/KLXVG5R444CQYIRGBG2WA7X73Y.json","view_paper":"https://pith.science/paper/KLXVG5R4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.11941&json=true","fetch_graph":"https://pith.science/api/pith-number/KLXVG5R444CQYIRGBG2WA7X73Y/graph.json","fetch_events":"https://pith.science/api/pith-number/KLXVG5R444CQYIRGBG2WA7X73Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KLXVG5R444CQYIRGBG2WA7X73Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KLXVG5R444CQYIRGBG2WA7X73Y/action/storage_attestation","attest_author":"https://pith.science/pith/KLXVG5R444CQYIRGBG2WA7X73Y/action/author_attestation","sign_citation":"https://pith.science/pith/KLXVG5R444CQYIRGBG2WA7X73Y/action/citation_signature","submit_replication":"https://pith.science/pith/KLXVG5R444CQYIRGBG2WA7X73Y/action/replication_record"}},"created_at":"2026-07-05T08:26:20.022070+00:00","updated_at":"2026-07-05T08:26:20.022070+00:00"}