{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XZAQNZDOD4G4YLKD42ZBY3GMGZ","short_pith_number":"pith:XZAQNZDO","schema_version":"1.0","canonical_sha256":"be4106e46e1f0dcc2d43e6b21c6ccc365d6fb2e9f4c1a0a100520752ee285414","source":{"kind":"arxiv","id":"2606.02355","version":1},"attestation_state":"computed","paper":{"title":"SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fei Huang, Ke Zeng, Leyi Wei, Lu Pan, Meng Hsuan Yu, Siyuan Chen, Tianyu Chen, Xiangrong Liu, Xingyang Li, Xunliang Cai, Yuanfan Li, Zhongyu He","submitted_at":"2026-06-01T15:02:59Z","abstract_excerpt":"Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or persistent skill retrieval at inference, increasing engineering complexity, context length, and deployment latency. We propose Self-Internalizing Reinforcement learning with Intrinsic skills (SIRI), a three-phase framework that enables agents to discover, validate, and internalize skills without external skill generators or inference-time skill banks. SIRI first warms up the policy with GiGPO to acquire basic interaction ability and collect succe"},"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":"2606.02355","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T15:02:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a31dd26a8e89bd05d541d9c67a26eec6fbfb6537500f05eb1420b8c436178267","abstract_canon_sha256":"10c06798f23c4ae50262f6a5ec51d7b7f19e697372de20de80777826aa721607"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T03:04:56.968780Z","signature_b64":"vF/DWJKzEw6veqO87T/AJGXBVTKPKKSNg95UIilVNO3aXtomj04ABhkiPrJwUv8sF2IcN62LPRUcpLDJ5R4ZCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be4106e46e1f0dcc2d43e6b21c6ccc365d6fb2e9f4c1a0a100520752ee285414","last_reissued_at":"2026-06-02T03:04:56.968393Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T03:04:56.968393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Fei Huang, Ke Zeng, Leyi Wei, Lu Pan, Meng Hsuan Yu, Siyuan Chen, Tianyu Chen, Xiangrong Liu, Xingyang Li, Xunliang Cai, Yuanfan Li, Zhongyu He","submitted_at":"2026-06-01T15:02:59Z","abstract_excerpt":"Long-horizon LLM agents can benefit from reusable skills, yet existing skill-based methods often rely on external skill generators during training or persistent skill retrieval at inference, increasing engineering complexity, context length, and deployment latency. We propose Self-Internalizing Reinforcement learning with Intrinsic skills (SIRI), a three-phase framework that enables agents to discover, validate, and internalize skills without external skill generators or inference-time skill banks. SIRI first warms up the policy with GiGPO to acquire basic interaction ability and collect succe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02355","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/2606.02355/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":"2606.02355","created_at":"2026-06-02T03:04:56.968450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02355v1","created_at":"2026-06-02T03:04:56.968450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02355","created_at":"2026-06-02T03:04:56.968450+00:00"},{"alias_kind":"pith_short_12","alias_value":"XZAQNZDOD4G4","created_at":"2026-06-02T03:04:56.968450+00:00"},{"alias_kind":"pith_short_16","alias_value":"XZAQNZDOD4G4YLKD","created_at":"2026-06-02T03:04:56.968450+00:00"},{"alias_kind":"pith_short_8","alias_value":"XZAQNZDO","created_at":"2026-06-02T03:04:56.968450+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/XZAQNZDOD4G4YLKD42ZBY3GMGZ","json":"https://pith.science/pith/XZAQNZDOD4G4YLKD42ZBY3GMGZ.json","graph_json":"https://pith.science/api/pith-number/XZAQNZDOD4G4YLKD42ZBY3GMGZ/graph.json","events_json":"https://pith.science/api/pith-number/XZAQNZDOD4G4YLKD42ZBY3GMGZ/events.json","paper":"https://pith.science/paper/XZAQNZDO"},"agent_actions":{"view_html":"https://pith.science/pith/XZAQNZDOD4G4YLKD42ZBY3GMGZ","download_json":"https://pith.science/pith/XZAQNZDOD4G4YLKD42ZBY3GMGZ.json","view_paper":"https://pith.science/paper/XZAQNZDO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02355&json=true","fetch_graph":"https://pith.science/api/pith-number/XZAQNZDOD4G4YLKD42ZBY3GMGZ/graph.json","fetch_events":"https://pith.science/api/pith-number/XZAQNZDOD4G4YLKD42ZBY3GMGZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XZAQNZDOD4G4YLKD42ZBY3GMGZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XZAQNZDOD4G4YLKD42ZBY3GMGZ/action/storage_attestation","attest_author":"https://pith.science/pith/XZAQNZDOD4G4YLKD42ZBY3GMGZ/action/author_attestation","sign_citation":"https://pith.science/pith/XZAQNZDOD4G4YLKD42ZBY3GMGZ/action/citation_signature","submit_replication":"https://pith.science/pith/XZAQNZDOD4G4YLKD42ZBY3GMGZ/action/replication_record"}},"created_at":"2026-06-02T03:04:56.968450+00:00","updated_at":"2026-06-02T03:04:56.968450+00:00"}