{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:P6LSS47WFI2KI7RUFQLJGUJE6H","short_pith_number":"pith:P6LSS47W","schema_version":"1.0","canonical_sha256":"7f972973f62a34a47e342c16935124f1cf1e3d06436950e0e12d63d65bc5fa10","source":{"kind":"arxiv","id":"2608.01234","version":1},"attestation_state":"computed","paper":{"title":"Learning What to Remember and What to Internalize in LLM Self-Evolution via Adaptive Memory-Parameter Coordination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hongbin Pei, Jiayu Liu, Tianyun Ji, Yu Su, Zhenya Huang, Zirui Liu","submitted_at":"2026-08-02T13:39:01Z","abstract_excerpt":"Large language model agents increasingly operate in dynamic environments where tool interfaces, APIs, and user requirements change after deployment. Existing self-evolution methods mainly follow two paradigms: harness-based approaches, which externalize feedback into editable memories or skills for rapid adaptation, and parameter-based approaches, which internalize experience into model parameters for deeper capability improvement. However, using either mechanism alone creates a trade-off between flexibility and performance. This paper asks how an agent can coordinate both channels to achieve "},"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":"2608.01234","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-08-02T13:39:01Z","cross_cats_sorted":[],"title_canon_sha256":"aa3e8e4c132533821f3aeee2c5f6aba832852aa1a43680c7cafa570b17011b6f","abstract_canon_sha256":"2f56f6facc81ce4b10af1b3d5c2c23c6b78926fda3875699b4f3fdcbb901b40e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-04T02:02:14.721342Z","signature_b64":"893LV+uNlFnFcd2wfL+KUrB477VF/xSP9ycUeoC4CqcgUk4CWG20j0wvI2SnmPUG26s4g7Vxvk0zlrHvy9I1Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7f972973f62a34a47e342c16935124f1cf1e3d06436950e0e12d63d65bc5fa10","last_reissued_at":"2026-08-04T02:02:14.717688Z","signature_status":"signed_v1","first_computed_at":"2026-08-04T02:02:14.717688Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning What to Remember and What to Internalize in LLM Self-Evolution via Adaptive Memory-Parameter Coordination","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Hongbin Pei, Jiayu Liu, Tianyun Ji, Yu Su, Zhenya Huang, Zirui Liu","submitted_at":"2026-08-02T13:39:01Z","abstract_excerpt":"Large language model agents increasingly operate in dynamic environments where tool interfaces, APIs, and user requirements change after deployment. Existing self-evolution methods mainly follow two paradigms: harness-based approaches, which externalize feedback into editable memories or skills for rapid adaptation, and parameter-based approaches, which internalize experience into model parameters for deeper capability improvement. However, using either mechanism alone creates a trade-off between flexibility and performance. This paper asks how an agent can coordinate both channels to achieve "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2608.01234","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/2608.01234/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":"2608.01234","created_at":"2026-08-04T02:02:14.719595+00:00"},{"alias_kind":"arxiv_version","alias_value":"2608.01234v1","created_at":"2026-08-04T02:02:14.719595+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2608.01234","created_at":"2026-08-04T02:02:14.719595+00:00"},{"alias_kind":"pith_short_12","alias_value":"P6LSS47WFI2K","created_at":"2026-08-04T02:02:14.719595+00:00"},{"alias_kind":"pith_short_16","alias_value":"P6LSS47WFI2KI7RU","created_at":"2026-08-04T02:02:14.719595+00:00"},{"alias_kind":"pith_short_8","alias_value":"P6LSS47W","created_at":"2026-08-04T02:02:14.719595+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/P6LSS47WFI2KI7RUFQLJGUJE6H","json":"https://pith.science/pith/P6LSS47WFI2KI7RUFQLJGUJE6H.json","graph_json":"https://pith.science/api/pith-number/P6LSS47WFI2KI7RUFQLJGUJE6H/graph.json","events_json":"https://pith.science/api/pith-number/P6LSS47WFI2KI7RUFQLJGUJE6H/events.json","paper":"https://pith.science/paper/P6LSS47W"},"agent_actions":{"view_html":"https://pith.science/pith/P6LSS47WFI2KI7RUFQLJGUJE6H","download_json":"https://pith.science/pith/P6LSS47WFI2KI7RUFQLJGUJE6H.json","view_paper":"https://pith.science/paper/P6LSS47W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2608.01234&json=true","fetch_graph":"https://pith.science/api/pith-number/P6LSS47WFI2KI7RUFQLJGUJE6H/graph.json","fetch_events":"https://pith.science/api/pith-number/P6LSS47WFI2KI7RUFQLJGUJE6H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P6LSS47WFI2KI7RUFQLJGUJE6H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P6LSS47WFI2KI7RUFQLJGUJE6H/action/storage_attestation","attest_author":"https://pith.science/pith/P6LSS47WFI2KI7RUFQLJGUJE6H/action/author_attestation","sign_citation":"https://pith.science/pith/P6LSS47WFI2KI7RUFQLJGUJE6H/action/citation_signature","submit_replication":"https://pith.science/pith/P6LSS47WFI2KI7RUFQLJGUJE6H/action/replication_record"}},"created_at":"2026-08-04T02:02:14.719595+00:00","updated_at":"2026-08-04T02:02:14.719595+00:00"}