{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X7552FTIVHU7ZCMKYE6N6QVZEZ","short_pith_number":"pith:X7552FTI","schema_version":"1.0","canonical_sha256":"bffbdd1668a9e9fc898ac13cdf42b9264ab62a4f02ac24ecd4bd2816e809d80f","source":{"kind":"arxiv","id":"2506.10387","version":1},"attestation_state":"computed","paper":{"title":"Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dongmei Jiang, Gongwei Chen, Kaiwen Zhou, Liqiang Nie, Rui Shao, Yinchuan Li, Yuquan Xie, Zaijing Li","submitted_at":"2025-06-12T06:21:19Z","abstract_excerpt":"Recent efforts to leverage the Multi-modal Large Language Model (MLLM) as GUI agents have yielded promising outcomes. However, these agents still struggle with long-horizon tasks in online environments, primarily due to insufficient knowledge and the inherent gap between offline and online domains. In this paper, inspired by how humans generalize knowledge in open-ended environments, we propose a Hierarchical Multimodal Skills (HMS) module to tackle the issue of insufficient knowledge. It progressively abstracts trajectories into execution skills, core skills, and ultimately meta-skills, provi"},"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":"2506.10387","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-06-12T06:21:19Z","cross_cats_sorted":[],"title_canon_sha256":"db52a7e42215ccd3ae6bab26b4e7b1e0582a2650468d5d5ecf16b420efe24d6f","abstract_canon_sha256":"55f50c08234be007cc8392ad1f83203b5ebd86a97c6314aea55af84ff058a689"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:20:22.472026Z","signature_b64":"P361C+txB5y7G02ACa1LKqLBujCHtDZMQyX/PInznqYZLdrRNMlU+agd/0nZbqukIrUteJ+YhwJQPGgTzTx+Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bffbdd1668a9e9fc898ac13cdf42b9264ab62a4f02ac24ecd4bd2816e809d80f","last_reissued_at":"2026-07-05T11:20:22.471515Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:20:22.471515Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mirage-1: Augmenting and Updating GUI Agent with Hierarchical Multimodal Skills","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Dongmei Jiang, Gongwei Chen, Kaiwen Zhou, Liqiang Nie, Rui Shao, Yinchuan Li, Yuquan Xie, Zaijing Li","submitted_at":"2025-06-12T06:21:19Z","abstract_excerpt":"Recent efforts to leverage the Multi-modal Large Language Model (MLLM) as GUI agents have yielded promising outcomes. However, these agents still struggle with long-horizon tasks in online environments, primarily due to insufficient knowledge and the inherent gap between offline and online domains. In this paper, inspired by how humans generalize knowledge in open-ended environments, we propose a Hierarchical Multimodal Skills (HMS) module to tackle the issue of insufficient knowledge. It progressively abstracts trajectories into execution skills, core skills, and ultimately meta-skills, provi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.10387","kind":"arxiv","version":1},"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/2506.10387/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":"2506.10387","created_at":"2026-07-05T11:20:22.471574+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.10387v1","created_at":"2026-07-05T11:20:22.471574+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.10387","created_at":"2026-07-05T11:20:22.471574+00:00"},{"alias_kind":"pith_short_12","alias_value":"X7552FTIVHU7","created_at":"2026-07-05T11:20:22.471574+00:00"},{"alias_kind":"pith_short_16","alias_value":"X7552FTIVHU7ZCMK","created_at":"2026-07-05T11:20:22.471574+00:00"},{"alias_kind":"pith_short_8","alias_value":"X7552FTI","created_at":"2026-07-05T11:20:22.471574+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22671","citing_title":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22671","citing_title":"From Abstraction to Instantiation: Learning Behavioral Representation for Vision-Language-Action Model","ref_index":27,"is_internal_anchor":false},{"citing_arxiv_id":"2510.24168","citing_title":"MGA: Memory-Driven GUI Agent for Observation-Centric Interaction","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2601.09636","citing_title":"PersonalAlign: Hierarchical Implicit Intent Alignment for Personalized GUI Agent with Long-Term User-Centric Records","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":31,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13527","citing_title":"MMSkills: Towards Multimodal Skills for General Visual Agents","ref_index":31,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X7552FTIVHU7ZCMKYE6N6QVZEZ","json":"https://pith.science/pith/X7552FTIVHU7ZCMKYE6N6QVZEZ.json","graph_json":"https://pith.science/api/pith-number/X7552FTIVHU7ZCMKYE6N6QVZEZ/graph.json","events_json":"https://pith.science/api/pith-number/X7552FTIVHU7ZCMKYE6N6QVZEZ/events.json","paper":"https://pith.science/paper/X7552FTI"},"agent_actions":{"view_html":"https://pith.science/pith/X7552FTIVHU7ZCMKYE6N6QVZEZ","download_json":"https://pith.science/pith/X7552FTIVHU7ZCMKYE6N6QVZEZ.json","view_paper":"https://pith.science/paper/X7552FTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.10387&json=true","fetch_graph":"https://pith.science/api/pith-number/X7552FTIVHU7ZCMKYE6N6QVZEZ/graph.json","fetch_events":"https://pith.science/api/pith-number/X7552FTIVHU7ZCMKYE6N6QVZEZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X7552FTIVHU7ZCMKYE6N6QVZEZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X7552FTIVHU7ZCMKYE6N6QVZEZ/action/storage_attestation","attest_author":"https://pith.science/pith/X7552FTIVHU7ZCMKYE6N6QVZEZ/action/author_attestation","sign_citation":"https://pith.science/pith/X7552FTIVHU7ZCMKYE6N6QVZEZ/action/citation_signature","submit_replication":"https://pith.science/pith/X7552FTIVHU7ZCMKYE6N6QVZEZ/action/replication_record"}},"created_at":"2026-07-05T11:20:22.471574+00:00","updated_at":"2026-07-05T11:20:22.471574+00:00"}