{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:V5T2IRJM6YB72EVSKAR6FE6MIT","short_pith_number":"pith:V5T2IRJM","schema_version":"1.0","canonical_sha256":"af67a4452cf603fd12b25023e293cc44c75d8f6ad638902010e3b00380c75800","source":{"kind":"arxiv","id":"2507.22925","version":1},"attestation_state":"computed","paper":{"title":"Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haoran Sun, Shaoning Zeng","submitted_at":"2025-07-23T12:45:44Z","abstract_excerpt":"Long-term memory is one of the key factors influencing the reasoning capabilities of Large Language Model Agents (LLM Agents). Incorporating a memory mechanism that effectively integrates past interactions can significantly enhance decision-making and contextual coherence of LLM Agents. While recent works have made progress in memory storage and retrieval, such as encoding memory into dense vectors for similarity-based search or organizing knowledge in the form of graph, these approaches often fall short in structured memory organization and efficient retrieval. To address these limitations, w"},"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":"2507.22925","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-23T12:45:44Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"4674af27067eee0a156a3126cc434afc8eb1efcb40b316dcfa13d413f95c299d","abstract_canon_sha256":"92740d7bd34cd46e583a39076b8fe5ecaf70b391399132bc2518c3dacf0bf608"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:46:01.963458Z","signature_b64":"B6MMHBudb724G/tt8R9ILj2h5nx0JhgrZEPoxjRvgm8IWQ/9MRls6mIWS9DFy1hlVOhwkStQs2sdaE8+CCV3DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"af67a4452cf603fd12b25023e293cc44c75d8f6ad638902010e3b00380c75800","last_reissued_at":"2026-07-05T11:46:01.962554Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:46:01.962554Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hierarchical Memory for High-Efficiency Long-Term Reasoning in LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Haoran Sun, Shaoning Zeng","submitted_at":"2025-07-23T12:45:44Z","abstract_excerpt":"Long-term memory is one of the key factors influencing the reasoning capabilities of Large Language Model Agents (LLM Agents). Incorporating a memory mechanism that effectively integrates past interactions can significantly enhance decision-making and contextual coherence of LLM Agents. While recent works have made progress in memory storage and retrieval, such as encoding memory into dense vectors for similarity-based search or organizing knowledge in the form of graph, these approaches often fall short in structured memory organization and efficient retrieval. To address these limitations, w"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22925","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/2507.22925/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":"2507.22925","created_at":"2026-07-05T11:46:01.962625+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22925v1","created_at":"2026-07-05T11:46:01.962625+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22925","created_at":"2026-07-05T11:46:01.962625+00:00"},{"alias_kind":"pith_short_12","alias_value":"V5T2IRJM6YB7","created_at":"2026-07-05T11:46:01.962625+00:00"},{"alias_kind":"pith_short_16","alias_value":"V5T2IRJM6YB72EVS","created_at":"2026-07-05T11:46:01.962625+00:00"},{"alias_kind":"pith_short_8","alias_value":"V5T2IRJM","created_at":"2026-07-05T11:46:01.962625+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22385","citing_title":"MetaPS: Adaptive Programmatic Strategy Selection for Market Agents","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31612","citing_title":"What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31612","citing_title":"What Memory Do GUI Agents Really Need? From Passive Records to Active Task-Driving States","ref_index":62,"is_internal_anchor":false},{"citing_arxiv_id":"2606.28566","citing_title":"R$^2$-Searcher: Calibrating Retrieval and Reasoning Boundaries for Agentic Search","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25680","citing_title":"Simulating Human Memory with Language Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2601.14724","citing_title":"HERMES: KV Cache as Hierarchical Memory for Efficient Streaming Video Understanding","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00702","citing_title":"Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19457","citing_title":"Four-Axis Decision Alignment for Long-Horizon Enterprise AI Agents","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11628","citing_title":"Back to Basics: Let Conversational Agents Remember with Just Retrieval and Generation","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18349","citing_title":"HiGMem: A Hierarchical and LLM-Guided Memory System for Long-Term Conversational Agents","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16774","citing_title":"Retention Consequence in Lifecycle Memory Control","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20158","citing_title":"Stateless Decision Memory for Enterprise AI Agents","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/V5T2IRJM6YB72EVSKAR6FE6MIT","json":"https://pith.science/pith/V5T2IRJM6YB72EVSKAR6FE6MIT.json","graph_json":"https://pith.science/api/pith-number/V5T2IRJM6YB72EVSKAR6FE6MIT/graph.json","events_json":"https://pith.science/api/pith-number/V5T2IRJM6YB72EVSKAR6FE6MIT/events.json","paper":"https://pith.science/paper/V5T2IRJM"},"agent_actions":{"view_html":"https://pith.science/pith/V5T2IRJM6YB72EVSKAR6FE6MIT","download_json":"https://pith.science/pith/V5T2IRJM6YB72EVSKAR6FE6MIT.json","view_paper":"https://pith.science/paper/V5T2IRJM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22925&json=true","fetch_graph":"https://pith.science/api/pith-number/V5T2IRJM6YB72EVSKAR6FE6MIT/graph.json","fetch_events":"https://pith.science/api/pith-number/V5T2IRJM6YB72EVSKAR6FE6MIT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V5T2IRJM6YB72EVSKAR6FE6MIT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V5T2IRJM6YB72EVSKAR6FE6MIT/action/storage_attestation","attest_author":"https://pith.science/pith/V5T2IRJM6YB72EVSKAR6FE6MIT/action/author_attestation","sign_citation":"https://pith.science/pith/V5T2IRJM6YB72EVSKAR6FE6MIT/action/citation_signature","submit_replication":"https://pith.science/pith/V5T2IRJM6YB72EVSKAR6FE6MIT/action/replication_record"}},"created_at":"2026-07-05T11:46:01.962625+00:00","updated_at":"2026-07-05T11:46:01.962625+00:00"}