{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C7HLZOAXOJ3SDEP3QANGWCGQAZ","short_pith_number":"pith:C7HLZOAX","schema_version":"1.0","canonical_sha256":"17cebcb81772772191fb801a6b08d00656c934e2ce2116def327f2eac5992f75","source":{"kind":"arxiv","id":"2404.18074","version":3},"attestation_state":"computed","paper":{"title":"MMAC-Copilot: Multi-modal Agent Collaboration Operating Copilot","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Ling Chen, Meng Fang, Xiuying Chen, Yanda Li, Yaohang Li, Yuan Huang, Zecheng Shi, Zhenhao Chen, Zirui Song","submitted_at":"2024-04-28T05:33:15Z","abstract_excerpt":"Large language model agents that interact with PC applications often face limitations due to their singular mode of interaction with real-world environments, leading to restricted versatility and frequent hallucinations. To address this, we propose the Multi-Modal Agent Collaboration framework (MMAC-Copilot), a framework utilizes the collective expertise of diverse agents to enhance interaction ability with application. The framework introduces a team collaboration chain, enabling each participating agent to contribute insights based on their specific domain knowledge, effectively reducing the"},"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":"2404.18074","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-04-28T05:33:15Z","cross_cats_sorted":["cs.HC"],"title_canon_sha256":"8cdabc6b2d0f9db8063a7b4fae9df8b97ac517eaca2baffe24a43a6c56d3988f","abstract_canon_sha256":"6dfce4fd3fdd02ea970e6d6662e6dc6a86d5a19de40fa9161bfa0fb650099f14"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:37:25.942994Z","signature_b64":"P6fdd65/c9BIwAPcd3/o5P0iIIDelE3e4wXd5gyR3fubUCcNXz14OVV3B4VGNI7oqNwaNjKT8eZVrdmICMgeDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"17cebcb81772772191fb801a6b08d00656c934e2ce2116def327f2eac5992f75","last_reissued_at":"2026-07-05T10:37:25.942158Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:37:25.942158Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMAC-Copilot: Multi-modal Agent Collaboration Operating Copilot","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.HC"],"primary_cat":"cs.AI","authors_text":"Ling Chen, Meng Fang, Xiuying Chen, Yanda Li, Yaohang Li, Yuan Huang, Zecheng Shi, Zhenhao Chen, Zirui Song","submitted_at":"2024-04-28T05:33:15Z","abstract_excerpt":"Large language model agents that interact with PC applications often face limitations due to their singular mode of interaction with real-world environments, leading to restricted versatility and frequent hallucinations. To address this, we propose the Multi-Modal Agent Collaboration framework (MMAC-Copilot), a framework utilizes the collective expertise of diverse agents to enhance interaction ability with application. The framework introduces a team collaboration chain, enabling each participating agent to contribute insights based on their specific domain knowledge, effectively reducing the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.18074","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/2404.18074/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":"2404.18074","created_at":"2026-07-05T10:37:25.942256+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.18074v3","created_at":"2026-07-05T10:37:25.942256+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.18074","created_at":"2026-07-05T10:37:25.942256+00:00"},{"alias_kind":"pith_short_12","alias_value":"C7HLZOAXOJ3S","created_at":"2026-07-05T10:37:25.942256+00:00"},{"alias_kind":"pith_short_16","alias_value":"C7HLZOAXOJ3SDEP3","created_at":"2026-07-05T10:37:25.942256+00:00"},{"alias_kind":"pith_short_8","alias_value":"C7HLZOAX","created_at":"2026-07-05T10:37:25.942256+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2501.16150","citing_title":"A Comprehensive Survey of Agents for Computer Use: Foundations, Challenges, and Future Directions","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2411.18279","citing_title":"Large Language Model-Brained GUI Agents: A Survey","ref_index":257,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C7HLZOAXOJ3SDEP3QANGWCGQAZ","json":"https://pith.science/pith/C7HLZOAXOJ3SDEP3QANGWCGQAZ.json","graph_json":"https://pith.science/api/pith-number/C7HLZOAXOJ3SDEP3QANGWCGQAZ/graph.json","events_json":"https://pith.science/api/pith-number/C7HLZOAXOJ3SDEP3QANGWCGQAZ/events.json","paper":"https://pith.science/paper/C7HLZOAX"},"agent_actions":{"view_html":"https://pith.science/pith/C7HLZOAXOJ3SDEP3QANGWCGQAZ","download_json":"https://pith.science/pith/C7HLZOAXOJ3SDEP3QANGWCGQAZ.json","view_paper":"https://pith.science/paper/C7HLZOAX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.18074&json=true","fetch_graph":"https://pith.science/api/pith-number/C7HLZOAXOJ3SDEP3QANGWCGQAZ/graph.json","fetch_events":"https://pith.science/api/pith-number/C7HLZOAXOJ3SDEP3QANGWCGQAZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C7HLZOAXOJ3SDEP3QANGWCGQAZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C7HLZOAXOJ3SDEP3QANGWCGQAZ/action/storage_attestation","attest_author":"https://pith.science/pith/C7HLZOAXOJ3SDEP3QANGWCGQAZ/action/author_attestation","sign_citation":"https://pith.science/pith/C7HLZOAXOJ3SDEP3QANGWCGQAZ/action/citation_signature","submit_replication":"https://pith.science/pith/C7HLZOAXOJ3SDEP3QANGWCGQAZ/action/replication_record"}},"created_at":"2026-07-05T10:37:25.942256+00:00","updated_at":"2026-07-05T10:37:25.942256+00:00"}