{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CB5EVLIPWM5YPP7UQ4XKKZBX5E","short_pith_number":"pith:CB5EVLIP","schema_version":"1.0","canonical_sha256":"107a4aad0fb33b87bff4872ea56437e91f048fc92cc451792ac24e0e54d4514a","source":{"kind":"arxiv","id":"2606.01414","version":1},"attestation_state":"computed","paper":{"title":"Agent Skills Should Go Beyond Text: The Case for Visual Skills","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binxiao Xu, Bocheng Zou, Hang Hua, Ruichuan An","submitted_at":"2026-05-31T19:22:43Z","abstract_excerpt":"Reusable skills are a key mechanism for extending agent capabilities, allowing agents to accumulate experience and solve increasingly complex tasks. Yet most existing skill-learning methods store reusable experience as text-only assets, such as instructions, reasoning traces, or summarized trajectories. We argue that this text-only paradigm creates a fundamental bottleneck for visual-centric tasks, where reusable knowledge often depends on spatial layout, visual grounding, fine-grained appearance, and localized state changes. To address this limitation, we propose \\textbf{\\NAME}, a multimodal "},"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":"2606.01414","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-31T19:22:43Z","cross_cats_sorted":[],"title_canon_sha256":"096d66cdab65bead6f1b93768adedf3e60a917094b643129707d111e062660d3","abstract_canon_sha256":"be04ba50d5032824705f93cc2b5deea2ba5cad221c27f0db9996a70b78703d85"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:04:32.679484Z","signature_b64":"cA1t2K9m9BCjhT6zN/uFq0mAQMtBsBWytUA94bX1VXCPMc6YaHkDHAd3g9DgjgjuV2j2mGgVH7lV7HhgnCHjBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"107a4aad0fb33b87bff4872ea56437e91f048fc92cc451792ac24e0e54d4514a","last_reissued_at":"2026-06-02T02:04:32.679125Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:04:32.679125Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Agent Skills Should Go Beyond Text: The Case for Visual Skills","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Binxiao Xu, Bocheng Zou, Hang Hua, Ruichuan An","submitted_at":"2026-05-31T19:22:43Z","abstract_excerpt":"Reusable skills are a key mechanism for extending agent capabilities, allowing agents to accumulate experience and solve increasingly complex tasks. Yet most existing skill-learning methods store reusable experience as text-only assets, such as instructions, reasoning traces, or summarized trajectories. We argue that this text-only paradigm creates a fundamental bottleneck for visual-centric tasks, where reusable knowledge often depends on spatial layout, visual grounding, fine-grained appearance, and localized state changes. To address this limitation, we propose \\textbf{\\NAME}, a multimodal "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.01414","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/2606.01414/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":"2606.01414","created_at":"2026-06-02T02:04:32.679182+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.01414v1","created_at":"2026-06-02T02:04:32.679182+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.01414","created_at":"2026-06-02T02:04:32.679182+00:00"},{"alias_kind":"pith_short_12","alias_value":"CB5EVLIPWM5Y","created_at":"2026-06-02T02:04:32.679182+00:00"},{"alias_kind":"pith_short_16","alias_value":"CB5EVLIPWM5YPP7U","created_at":"2026-06-02T02:04:32.679182+00:00"},{"alias_kind":"pith_short_8","alias_value":"CB5EVLIP","created_at":"2026-06-02T02:04:32.679182+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CB5EVLIPWM5YPP7UQ4XKKZBX5E","json":"https://pith.science/pith/CB5EVLIPWM5YPP7UQ4XKKZBX5E.json","graph_json":"https://pith.science/api/pith-number/CB5EVLIPWM5YPP7UQ4XKKZBX5E/graph.json","events_json":"https://pith.science/api/pith-number/CB5EVLIPWM5YPP7UQ4XKKZBX5E/events.json","paper":"https://pith.science/paper/CB5EVLIP"},"agent_actions":{"view_html":"https://pith.science/pith/CB5EVLIPWM5YPP7UQ4XKKZBX5E","download_json":"https://pith.science/pith/CB5EVLIPWM5YPP7UQ4XKKZBX5E.json","view_paper":"https://pith.science/paper/CB5EVLIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.01414&json=true","fetch_graph":"https://pith.science/api/pith-number/CB5EVLIPWM5YPP7UQ4XKKZBX5E/graph.json","fetch_events":"https://pith.science/api/pith-number/CB5EVLIPWM5YPP7UQ4XKKZBX5E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CB5EVLIPWM5YPP7UQ4XKKZBX5E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CB5EVLIPWM5YPP7UQ4XKKZBX5E/action/storage_attestation","attest_author":"https://pith.science/pith/CB5EVLIPWM5YPP7UQ4XKKZBX5E/action/author_attestation","sign_citation":"https://pith.science/pith/CB5EVLIPWM5YPP7UQ4XKKZBX5E/action/citation_signature","submit_replication":"https://pith.science/pith/CB5EVLIPWM5YPP7UQ4XKKZBX5E/action/replication_record"}},"created_at":"2026-06-02T02:04:32.679182+00:00","updated_at":"2026-06-02T02:04:32.679182+00:00"}