{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CXNSU3745B2NGTOIOI74WJSHG4","short_pith_number":"pith:CXNSU374","schema_version":"1.0","canonical_sha256":"15db2a6ffce874d34dc8723fcb2647371d84bfcd355cacff35ecde9646ce2e11","source":{"kind":"arxiv","id":"2607.25853","version":1},"attestation_state":"computed","paper":{"title":"HiSkill: Empowering LLM Agents with Hierarchical Skill Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng Yang, Chuan Shi, Jinxuan Cai, Qi Zhang, Yawen Li, Yu Hao, Zhiqiang Zhang","submitted_at":"2026-07-28T15:25:47Z","abstract_excerpt":"Skills have become an important abstraction for enabling large language model (LLM) agents to reuse past experience in long-horizon interactive tasks. However, existing trajectory-to-skill methods often produce flat collections of high-level textual skills that are stored and retrieved independently, leaving skill relations underutilized and maintaining a gap between high-level skills and executable actions. In this paper, we propose HiSkill, a hierarchical skill graph framework that organizes interaction trajectories into a directed graph with skill nodes, AtomicOp nodes, and typed edges. Spe"},"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":"2607.25853","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-07-28T15:25:47Z","cross_cats_sorted":[],"title_canon_sha256":"be6acfb8146b79cfd3baa60e8061fcf933a7c5998584a9cf59351f0cdd115658","abstract_canon_sha256":"86f82f18da52a5d89a1b774640e02a1576a83aeb68029edbe27ca830d25be1e5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-29T01:26:06.801900Z","signature_b64":"coZ5gBdfLrr7QmY0Fz1yXc/Ux3jsaSdlA/a9BBm5QYv7nOEj9DHdq+ugMB1FI+PuoS4LM7CRAbkr/q9bKEs9AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"15db2a6ffce874d34dc8723fcb2647371d84bfcd355cacff35ecde9646ce2e11","last_reissued_at":"2026-07-29T01:26:06.801025Z","signature_status":"signed_v1","first_computed_at":"2026-07-29T01:26:06.801025Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HiSkill: Empowering LLM Agents with Hierarchical Skill Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Cheng Yang, Chuan Shi, Jinxuan Cai, Qi Zhang, Yawen Li, Yu Hao, Zhiqiang Zhang","submitted_at":"2026-07-28T15:25:47Z","abstract_excerpt":"Skills have become an important abstraction for enabling large language model (LLM) agents to reuse past experience in long-horizon interactive tasks. However, existing trajectory-to-skill methods often produce flat collections of high-level textual skills that are stored and retrieved independently, leaving skill relations underutilized and maintaining a gap between high-level skills and executable actions. In this paper, we propose HiSkill, a hierarchical skill graph framework that organizes interaction trajectories into a directed graph with skill nodes, AtomicOp nodes, and typed edges. Spe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.25853","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/2607.25853/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":"2607.25853","created_at":"2026-07-29T01:26:06.801468+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.25853v1","created_at":"2026-07-29T01:26:06.801468+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.25853","created_at":"2026-07-29T01:26:06.801468+00:00"},{"alias_kind":"pith_short_12","alias_value":"CXNSU3745B2N","created_at":"2026-07-29T01:26:06.801468+00:00"},{"alias_kind":"pith_short_16","alias_value":"CXNSU3745B2NGTOI","created_at":"2026-07-29T01:26:06.801468+00:00"},{"alias_kind":"pith_short_8","alias_value":"CXNSU374","created_at":"2026-07-29T01:26:06.801468+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/CXNSU3745B2NGTOIOI74WJSHG4","json":"https://pith.science/pith/CXNSU3745B2NGTOIOI74WJSHG4.json","graph_json":"https://pith.science/api/pith-number/CXNSU3745B2NGTOIOI74WJSHG4/graph.json","events_json":"https://pith.science/api/pith-number/CXNSU3745B2NGTOIOI74WJSHG4/events.json","paper":"https://pith.science/paper/CXNSU374"},"agent_actions":{"view_html":"https://pith.science/pith/CXNSU3745B2NGTOIOI74WJSHG4","download_json":"https://pith.science/pith/CXNSU3745B2NGTOIOI74WJSHG4.json","view_paper":"https://pith.science/paper/CXNSU374","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.25853&json=true","fetch_graph":"https://pith.science/api/pith-number/CXNSU3745B2NGTOIOI74WJSHG4/graph.json","fetch_events":"https://pith.science/api/pith-number/CXNSU3745B2NGTOIOI74WJSHG4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CXNSU3745B2NGTOIOI74WJSHG4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CXNSU3745B2NGTOIOI74WJSHG4/action/storage_attestation","attest_author":"https://pith.science/pith/CXNSU3745B2NGTOIOI74WJSHG4/action/author_attestation","sign_citation":"https://pith.science/pith/CXNSU3745B2NGTOIOI74WJSHG4/action/citation_signature","submit_replication":"https://pith.science/pith/CXNSU3745B2NGTOIOI74WJSHG4/action/replication_record"}},"created_at":"2026-07-29T01:26:06.801468+00:00","updated_at":"2026-07-29T01:26:06.801468+00:00"}