{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:6NNSXFBK6JBRECCHR6FPCG4WHA","short_pith_number":"pith:6NNSXFBK","schema_version":"1.0","canonical_sha256":"f35b2b942af2431208478f8af11b96380278171da2b0364f3fa142ea963092bc","source":{"kind":"arxiv","id":"2504.15965","version":2},"attestation_state":"computed","paper":{"title":"From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"This survey connects categories of human memory to memory in LLM-based AI systems and introduces a three-dimension eight-quadrant framework to organize the field.","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chen Zhang, Huifeng Guo, Ruiming Tang, Sheng Liang, Yaxiong Wu, Yichao Wang, Yong Liu, Yongyue Zhang","submitted_at":"2025-04-22T15:05:04Z","abstract_excerpt":"Memory is the process of encoding, storing, and retrieving information, allowing humans to retain experiences, knowledge, skills, and facts over time, and serving as the foundation for growth and effective interaction with the world. It plays a crucial role in shaping our identity, making decisions, learning from past experiences, building relationships, and adapting to changes. In the era of large language models (LLMs), memory refers to the ability of an AI system to retain, recall, and use information from past interactions to improve future responses and interactions. Although previous res"},"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":true,"formal_links_present":false},"canonical_record":{"source":{"id":"2504.15965","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2025-04-22T15:05:04Z","cross_cats_sorted":[],"title_canon_sha256":"c1117039836b0cd39e8974d289ea220b57779280da231b4218865445e95a4f0c","abstract_canon_sha256":"9be892aae9b3f4d12be10420456503b63419743cb342f499aaf56b33bf96c06c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:38:14.287999Z","signature_b64":"fLtMVyeBaQ6jR+9KYP4mXemBKREOZAaJIiObfhlo25Cuv06oXPpoIQlY6XTaUOR1YkeneuKz5z97lJw8Lg6gAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f35b2b942af2431208478f8af11b96380278171da2b0364f3fa142ea963092bc","last_reissued_at":"2026-05-17T23:38:14.287425Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:38:14.287425Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"From Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"This survey connects categories of human memory to memory in LLM-based AI systems and introduces a three-dimension eight-quadrant framework to organize the field.","cross_cats":[],"primary_cat":"cs.IR","authors_text":"Chen Zhang, Huifeng Guo, Ruiming Tang, Sheng Liang, Yaxiong Wu, Yichao Wang, Yong Liu, Yongyue Zhang","submitted_at":"2025-04-22T15:05:04Z","abstract_excerpt":"Memory is the process of encoding, storing, and retrieving information, allowing humans to retain experiences, knowledge, skills, and facts over time, and serving as the foundation for growth and effective interaction with the world. It plays a crucial role in shaping our identity, making decisions, learning from past experiences, building relationships, and adapting to changes. In the era of large language models (LLMs), memory refers to the ability of an AI system to retain, recall, and use information from past interactions to improve future responses and interactions. Although previous res"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"we propose a comprehensive survey on the memory of LLM-driven AI systems. In particular, we first conduct a detailed analysis of the categories of human memory and relate them to the memory of AI systems. Second, we systematically organize existing memory-related work and propose a categorization method based on three dimensions (object, form, and time) and eight quadrants.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That mapping human memory categories directly to AI memory systems and organizing the literature via the proposed three-dimension eight-quadrant scheme will yield actionable insights for building more powerful memory mechanisms in LLMs.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"The paper surveys human memory categories, maps them to LLM memory, and proposes a new three-dimension (object, form, time) categorization into eight quadrants to organize existing work and highlight open problems.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"This survey connects categories of human memory to memory in LLM-based AI systems and introduces a three-dimension eight-quadrant framework to organize the field.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"25e3be365ff61a1501db3bffd21ae6d7d2de9fccdcd985fe3954c17e6520b4d2"},"source":{"id":"2504.15965","kind":"arxiv","version":2},"verdict":{"id":"1392be2b-7bf3-4642-91fc-9aff9faa45da","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-17T11:00:17.372542Z","strongest_claim":"we propose a comprehensive survey on the memory of LLM-driven AI systems. In particular, we first conduct a detailed analysis of the categories of human memory and relate them to the memory of AI systems. Second, we systematically organize existing memory-related work and propose a categorization method based on three dimensions (object, form, and time) and eight quadrants.","one_line_summary":"The paper surveys human memory categories, maps them to LLM memory, and proposes a new three-dimension (object, form, time) categorization into eight quadrants to organize existing work and highlight open problems.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That mapping human memory categories directly to AI memory systems and organizing the literature via the proposed three-dimension eight-quadrant scheme will yield actionable insights for building more powerful memory mechanisms in LLMs.","pith_extraction_headline":"This survey connects categories of human memory to memory in LLM-based AI systems and introduces a three-dimension eight-quadrant framework to organize the field."},"references":{"count":155,"sample":[{"doi":"","year":2024,"title":"A survey on large language model based autonomous agents","work_id":"b2aac465-d452-4d47-87d9-156aa944bc8c","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"Personal LLM Agents: Insights and Survey about the Capability, Efficiency and Security","work_id":"7692e42c-c83d-4527-ba16-9c4b69666d47","ref_index":2,"cited_arxiv_id":"2401.05459","is_internal_anchor":true},{"doi":"","year":2023,"title":"A Survey of Large Language Models","work_id":"de1b42b5-4a0a-4b1f-8c78-1f7fe21be6c9","ref_index":3,"cited_arxiv_id":"2303.18223","is_internal_anchor":true},{"doi":"","year":2024,"title":"A survey on evaluation of large language models","work_id":"abb4c0f1-6bc9-4f60-8dac-91f21de84748","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2024,"title":"All roads lead to rome: Unveiling the trajectory of recommender systems across the llm era","work_id":"c7931a4a-92fd-449d-b717-8df2c0c628e2","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":155,"snapshot_sha256":"3676b7cebf48137207e41164e4a181d609ef71ea202a34b55f8972983bcb1de3","internal_anchors":25},"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":"2504.15965","created_at":"2026-05-17T23:38:14.287521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.15965v2","created_at":"2026-05-17T23:38:14.287521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.15965","created_at":"2026-05-17T23:38:14.287521+00:00"},{"alias_kind":"pith_short_12","alias_value":"6NNSXFBK6JBR","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_16","alias_value":"6NNSXFBK6JBRECCH","created_at":"2026-05-18T12:33:37.589309+00:00"},{"alias_kind":"pith_short_8","alias_value":"6NNSXFBK","created_at":"2026-05-18T12:33:37.589309+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":23,"sample":[{"citing_arxiv_id":"2605.22411","citing_title":"DeferMem: Query-Time Evidence Distillation via Reinforcement Learning for Long-Term Memory QA","ref_index":45,"is_internal_anchor":true},{"citing_arxiv_id":"2605.18747","citing_title":"Code as Agent Harness","ref_index":187,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17830","citing_title":"Remembering More, Risking More: Longitudinal Safety Risks in Memory-Equipped LLM Agents","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2509.02547","citing_title":"The Landscape of Agentic Reinforcement Learning for LLMs: A Survey","ref_index":129,"is_internal_anchor":true},{"citing_arxiv_id":"2602.05467","citing_title":"MerNav: A Highly Generalizable Memory-Execute-Review Framework for Zero-Shot Object Goal Navigation","ref_index":10,"is_internal_anchor":true},{"citing_arxiv_id":"2507.03724","citing_title":"MemOS: A Memory OS for AI System","ref_index":20,"is_internal_anchor":true},{"citing_arxiv_id":"2603.29002","citing_title":"Understand and Accelerate Memory Processing Pipeline for Disaggregated LLM Inference","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07912","citing_title":"Sycophantic AI makes human interaction feel more effortful and less satisfying over time","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12213","citing_title":"Goal-Oriented Reasoning for RAG-based Memory in Conversational Agentic LLM Systems","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2605.12061","citing_title":"SAGE: A Self-Evolving Agentic Graph-Memory Engine for Structure-Aware Associative Memory","ref_index":254,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09330","citing_title":"The Trap of Trajectory: Towards Understanding and Mitigating Spurious Correlations in Agentic Memory","ref_index":54,"is_internal_anchor":true},{"citing_arxiv_id":"2605.09278","citing_title":"EquiMem: Calibrating Shared Memory in Multi-Agent Debate via Game-Theoretic Equilibrium","ref_index":80,"is_internal_anchor":true},{"citing_arxiv_id":"2604.27859","citing_title":"Rethinking Agentic Reinforcement Learning In Large Language Models","ref_index":102,"is_internal_anchor":true},{"citing_arxiv_id":"2605.00702","citing_title":"Learning How and What to Memorize: Cognition-Inspired Two-Stage Optimization for Evolving Memory","ref_index":162,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12034","citing_title":"Memory as Metabolism: A Design for Companion Knowledge Systems","ref_index":44,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07894","citing_title":"TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation","ref_index":74,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07877","citing_title":"MemReader: From Passive to Active Extraction for Long-Term Agent Memory","ref_index":1,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07912","citing_title":"Sycophantic AI makes human interaction feel more effortful and less satisfying over time","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.05719","citing_title":"Hackers or Hallucinators? A Comprehensive Analysis of LLM-Based Automated Penetration Testing","ref_index":119,"is_internal_anchor":true},{"citing_arxiv_id":"2604.06845","citing_title":"HingeMem: Boundary Guided Long-Term Memory with Query Adaptive Retrieval for Scalable Dialogues","ref_index":52,"is_internal_anchor":true},{"citing_arxiv_id":"2604.17265","citing_title":"MemSearch-o1: Empowering Large Language Models with Reasoning-Aligned Memory Growth in Agentic Search","ref_index":1,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6NNSXFBK6JBRECCHR6FPCG4WHA","json":"https://pith.science/pith/6NNSXFBK6JBRECCHR6FPCG4WHA.json","graph_json":"https://pith.science/api/pith-number/6NNSXFBK6JBRECCHR6FPCG4WHA/graph.json","events_json":"https://pith.science/api/pith-number/6NNSXFBK6JBRECCHR6FPCG4WHA/events.json","paper":"https://pith.science/paper/6NNSXFBK"},"agent_actions":{"view_html":"https://pith.science/pith/6NNSXFBK6JBRECCHR6FPCG4WHA","download_json":"https://pith.science/pith/6NNSXFBK6JBRECCHR6FPCG4WHA.json","view_paper":"https://pith.science/paper/6NNSXFBK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.15965&json=true","fetch_graph":"https://pith.science/api/pith-number/6NNSXFBK6JBRECCHR6FPCG4WHA/graph.json","fetch_events":"https://pith.science/api/pith-number/6NNSXFBK6JBRECCHR6FPCG4WHA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6NNSXFBK6JBRECCHR6FPCG4WHA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6NNSXFBK6JBRECCHR6FPCG4WHA/action/storage_attestation","attest_author":"https://pith.science/pith/6NNSXFBK6JBRECCHR6FPCG4WHA/action/author_attestation","sign_citation":"https://pith.science/pith/6NNSXFBK6JBRECCHR6FPCG4WHA/action/citation_signature","submit_replication":"https://pith.science/pith/6NNSXFBK6JBRECCHR6FPCG4WHA/action/replication_record"}},"created_at":"2026-05-17T23:38:14.287521+00:00","updated_at":"2026-05-17T23:38:14.287521+00:00"}