{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YJMP26CEC55VJSQPGGTZRMTFLF","short_pith_number":"pith:YJMP26CE","schema_version":"1.0","canonical_sha256":"c258fd7844177b54ca0f31a798b2655961fbe4367a53b70b3126b056b0d71056","source":{"kind":"arxiv","id":"2502.14282","version":2},"attestation_state":"computed","paper":{"title":"PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Chunfeng Yuan, Fei Huang, Haiyang Xu, Haowei Liu, Ji Zhang, Junyang Wang, Ming Yan, Weiming Hu, Xi Zhang, Yuyang Wanyan","submitted_at":"2025-02-20T05:41:55Z","abstract_excerpt":"In the field of MLLM-based GUI agents, compared to smartphones, the PC scenario not only features a more complex interactive environment, but also involves more intricate intra- and inter-app workflows. To address these issues, we propose a hierarchical agent framework named PC-Agent. Specifically, from the perception perspective, we devise an Active Perception Module (APM) to overcome the inadequate abilities of current MLLMs in perceiving screenshot content. From the decision-making perspective, to handle complex user instructions and interdependent subtasks more effectively, we propose a hi"},"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":"2502.14282","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-20T05:41:55Z","cross_cats_sorted":[],"title_canon_sha256":"ff149457c71a1488cac99d33b7f37ffcff5ebe61db151f67ef9068fe613b5d44","abstract_canon_sha256":"8a91b7721514ea36cb97044c5e364d9fdb7c44ddaac0ef4b1167ac48180dda4e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:54.880922Z","signature_b64":"YMMNyV8RU6W83SMcIaWfoBXkpTmyOcQAQ5DgHiG5DKHBVOWyqKP7LtQcrIVdBj7mJsia4O+dxY7J+Wa87oLXBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c258fd7844177b54ca0f31a798b2655961fbe4367a53b70b3126b056b0d71056","last_reissued_at":"2026-07-05T10:17:54.880478Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:54.880478Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PC-Agent: A Hierarchical Multi-Agent Collaboration Framework for Complex Task Automation on PC","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Changsheng Xu, Chunfeng Yuan, Fei Huang, Haiyang Xu, Haowei Liu, Ji Zhang, Junyang Wang, Ming Yan, Weiming Hu, Xi Zhang, Yuyang Wanyan","submitted_at":"2025-02-20T05:41:55Z","abstract_excerpt":"In the field of MLLM-based GUI agents, compared to smartphones, the PC scenario not only features a more complex interactive environment, but also involves more intricate intra- and inter-app workflows. To address these issues, we propose a hierarchical agent framework named PC-Agent. Specifically, from the perception perspective, we devise an Active Perception Module (APM) to overcome the inadequate abilities of current MLLMs in perceiving screenshot content. From the decision-making perspective, to handle complex user instructions and interdependent subtasks more effectively, we propose a hi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.14282","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/2502.14282/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":"2502.14282","created_at":"2026-07-05T10:17:54.880536+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.14282v2","created_at":"2026-07-05T10:17:54.880536+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.14282","created_at":"2026-07-05T10:17:54.880536+00:00"},{"alias_kind":"pith_short_12","alias_value":"YJMP26CEC55V","created_at":"2026-07-05T10:17:54.880536+00:00"},{"alias_kind":"pith_short_16","alias_value":"YJMP26CEC55VJSQP","created_at":"2026-07-05T10:17:54.880536+00:00"},{"alias_kind":"pith_short_8","alias_value":"YJMP26CE","created_at":"2026-07-05T10:17:54.880536+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":8,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11042","citing_title":"Workflow-GYM: Towards Long-Horizon Evaluation of Computer-use Agentic tasks in Real-World Professional Fields","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31410","citing_title":"Xiaomi-GUI-0 Technical Report","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31410","citing_title":"Xiaomi-GUI-0 Technical Report","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13228","citing_title":"ReTool-Video: Recursive Tool-Using Video Agents with Meta-Augmented Tool Grounding","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12481","citing_title":"ToolCUA: Towards Optimal GUI-Tool Path Orchestration for Computer Use Agents","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27699","citing_title":"Bridging Values and Behavior: A Hierarchical Framework for Proactive Embodied Agents","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25975","citing_title":"Rethinking KV Cache Eviction via a Unified Information-Theoretic Objective","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07505","citing_title":"LiteGUI: Distilling Compact GUI Agents with Reinforcement Learning","ref_index":5,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YJMP26CEC55VJSQPGGTZRMTFLF","json":"https://pith.science/pith/YJMP26CEC55VJSQPGGTZRMTFLF.json","graph_json":"https://pith.science/api/pith-number/YJMP26CEC55VJSQPGGTZRMTFLF/graph.json","events_json":"https://pith.science/api/pith-number/YJMP26CEC55VJSQPGGTZRMTFLF/events.json","paper":"https://pith.science/paper/YJMP26CE"},"agent_actions":{"view_html":"https://pith.science/pith/YJMP26CEC55VJSQPGGTZRMTFLF","download_json":"https://pith.science/pith/YJMP26CEC55VJSQPGGTZRMTFLF.json","view_paper":"https://pith.science/paper/YJMP26CE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.14282&json=true","fetch_graph":"https://pith.science/api/pith-number/YJMP26CEC55VJSQPGGTZRMTFLF/graph.json","fetch_events":"https://pith.science/api/pith-number/YJMP26CEC55VJSQPGGTZRMTFLF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YJMP26CEC55VJSQPGGTZRMTFLF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YJMP26CEC55VJSQPGGTZRMTFLF/action/storage_attestation","attest_author":"https://pith.science/pith/YJMP26CEC55VJSQPGGTZRMTFLF/action/author_attestation","sign_citation":"https://pith.science/pith/YJMP26CEC55VJSQPGGTZRMTFLF/action/citation_signature","submit_replication":"https://pith.science/pith/YJMP26CEC55VJSQPGGTZRMTFLF/action/replication_record"}},"created_at":"2026-07-05T10:17:54.880536+00:00","updated_at":"2026-07-05T10:17:54.880536+00:00"}