{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XZAQNZDOD4G4YLKD42ZBY3GMGZ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"10c06798f23c4ae50262f6a5ec51d7b7f19e697372de20de80777826aa721607","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T15:02:59Z","title_canon_sha256":"a31dd26a8e89bd05d541d9c67a26eec6fbfb6537500f05eb1420b8c436178267"},"schema_version":"1.0","source":{"id":"2606.02355","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.02355","created_at":"2026-06-02T03:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"2606.02355v1","created_at":"2026-06-02T03:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02355","created_at":"2026-06-02T03:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"XZAQNZDOD4G4","created_at":"2026-06-02T03:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"XZAQNZDOD4G4YLKD","created_at":"2026-06-02T03:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"XZAQNZDO","created_at":"2026-06-02T03:04:56Z"}],"graph_snapshots":[{"event_id":"sha256:564d804f067c7c4044ce3b19fc2fcf330386f1c6e8c5e8d4db4fdccda085a4fe","target":"graph","created_at":"2026-06-02T03:04:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2606.02355/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T15:02:59Z","title":"SIRI: Self-Internalizing Reinforcement Learning with Intrinsic Skills for LLM Agent Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02355","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:6f820f3961b4d29cfda793ec9e2347023b6f0907fa349f19b6544f4b305590ec","target":"record","created_at":"2026-06-02T03:04:56Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"10c06798f23c4ae50262f6a5ec51d7b7f19e697372de20de80777826aa721607","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-01T15:02:59Z","title_canon_sha256":"a31dd26a8e89bd05d541d9c67a26eec6fbfb6537500f05eb1420b8c436178267"},"schema_version":"1.0","source":{"id":"2606.02355","kind":"arxiv","version":1}},"canonical_sha256":"be4106e46e1f0dcc2d43e6b21c6ccc365d6fb2e9f4c1a0a100520752ee285414","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"be4106e46e1f0dcc2d43e6b21c6ccc365d6fb2e9f4c1a0a100520752ee285414","first_computed_at":"2026-06-02T03:04:56.968393Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T03:04:56.968393Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vF/DWJKzEw6veqO87T/AJGXBVTKPKKSNg95UIilVNO3aXtomj04ABhkiPrJwUv8sF2IcN62LPRUcpLDJ5R4ZCg==","signature_status":"signed_v1","signed_at":"2026-06-02T03:04:56.968780Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.02355","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6f820f3961b4d29cfda793ec9e2347023b6f0907fa349f19b6544f4b305590ec","sha256:564d804f067c7c4044ce3b19fc2fcf330386f1c6e8c5e8d4db4fdccda085a4fe"],"state_sha256":"e43bbc87bab8bdc54ba17bfacf0d2dbe0bd666dea548e45f955580a08033af61"}