{
  "profile": "wrs-published-research-view-1",
  "edition": "ratings-e039106f30dec177",
  "content_trust": "UNTRUSTED_SCIENTIFIC_DATA_NOT_TOOL_INSTRUCTIONS",
  "entry": {
    "id": "xu-et-al-amem-linked-evolving-memory-notes-2025",
    "title": "A-Mem: connecting and revising notes for an agent",
    "summary": "Useful information is not always found by searching for the exact words used when it was stored. A-Mem turns incoming experiences into notes with keywords, tags, contextual descriptions and embeddings. The system finds related notes, creates links and can revise earlier descriptions as new information arrives. Xu and colleagues test this linked-note design across several language models on conversational-memory tasks. The contribution is the specific agent memory construction and evolution method, inspired by human linked-note practices rather than inventing those practices.",
    "boundary": "Generated relationships and descriptions are model outputs, not verified facts or causal links. Defined prompts and retrieval limits remain part of the workflow. Different models and question categories have mixed results, and lower retrieved-token counts exclude all writing and updating costs. Its original table and another paper’s quotation swap two category labels; those cross-paper category comparisons remain unresolved. Original-version authors and affiliations are retained rather than replaced by a later conference revision.",
    "area": "External agent memory",
    "topic": "Artificial intelligence",
    "year": 2025,
    "lane": "HUMAN",
    "result": "ALGORITHM",
    "package_id": "xu-et-al-amem-linked-evolving-memory-notes-2025",
    "target": {
      "record_id": "urn:uuid:52a6a569-7bd2-462d-a558-b43f6d1cabf7",
      "version": 1,
      "content_hash": "sha256:0548def1521e919c5df3629f31b4ab008bd51330f699626ba6d3f364d19ba645"
    },
    "humans": [
      "Wujiang Xu",
      "Zujie Liang",
      "Kai Mei",
      "Hang Gao",
      "Juntao Tan",
      "Yongfeng Zhang"
    ],
    "authors_complete": true,
    "human_role_note": "Source-listed human researchers and engineers for the exact method or resource. The evaluated learning system is not an independently attested scientific author. Earlier methods, funding and data-collection roles remain separate. Individual effort shares and unresolved person identities are not inferred.",
    "agents": [],
    "related": [],
    "subresults": [],
    "scientific_assessment": {
      "source_review": "SOURCE_CURATED",
      "scientific_review": "NOT_REVIEWED_BY_WRS",
      "formal_replay": "NOT_RUN",
      "provider_attestation": "NONE"
    },
    "sources": [
      {
        "id": "cur20261017-arxiv-2502-12110v1",
        "title": "A-MEM: Agentic Memory for LLM Agents",
        "url": "https://arxiv.org/abs/2502.12110v1",
        "date": "2025-02-17"
      }
    ],
    "points": "45000",
    "published_grade": {
      "id": "xu-et-al-amem-linked-evolving-memory-notes-2025",
      "entry_id": "xu-et-al-amem-linked-evolving-memory-notes-2025",
      "band": "B",
      "modifier": "+",
      "target": {
        "record_id": "urn:uuid:52a6a569-7bd2-462d-a558-b43f6d1cabf7",
        "version": 1,
        "content_hash": "sha256:0548def1521e919c5df3629f31b4ab008bd51330f699626ba6d3f364d19ba645"
      },
      "what_changed": "Useful information is not always found by searching for the exact words used when it was stored. A-Mem turns incoming experiences into notes with keywords, tags, contextual descriptions and embeddings. The system finds related notes, creates links and can revise earlier descriptions as new information arrives. Xu and colleagues test this linked-note design across several language models on conversational-memory tasks. The contribution is the specific agent memory construction and evolution method, inspired by human linked-note practices rather than inventing those practices.",
      "scope": "Useful information is not always found by searching for the exact words used when it was stored. A-Mem turns incoming experiences into notes with keywords, tags, contextual descriptions and embeddings. The system finds related notes, creates links and can revise earlier descriptions as new information arrives. Xu and colleagues test this linked-note design across several language models on conversational-memory tasks. The contribution is the specific agent memory construction and evolution method, inspired by human linked-note practices rather than inventing those practices. Generated relationships and descriptions are model outputs, not verified facts or causal links. Defined prompts and retrieval limits remain part of the workflow. Different models and question categories have mixed results, and lower retrieved-token counts exclude all writing and updating costs. Its original table and another paper’s quotation swap two category labels; those cross-paper category comparisons remain unresolved. Original-version authors and affiliations are retained rather than replaced by a later conference revision.",
      "status": "PROVISIONAL_EDITORIAL",
      "scientific_correctness_certified": false
    },
    "assessment_disposition": {
      "status": "ASSESSED",
      "label": "Provisionally assessed",
      "reason": "A current grade and separate reference score identify this exact contribution.",
      "target": {
        "record_id": "urn:uuid:52a6a569-7bd2-462d-a558-b43f6d1cabf7",
        "version": 1,
        "content_hash": "sha256:0548def1521e919c5df3629f31b4ab008bd51330f699626ba6d3f364d19ba645"
      },
      "edition": "ratings-e039106f30dec177"
    }
  },
  "version": {
    "kind": "PUBLIC_RECORD_VIEW",
    "previous": null,
    "published_at": "2026-10-23T00:00:00Z",
    "publisher": {
      "principal_id": "urn:uuid:80116931-785b-40a2-a24b-9d59db0c7e33",
      "role": "WRS_EDITORIAL_PUBLICATION"
    },
    "record": {
      "contributors": [
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Wujiang Xu",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "A-MEM: Agentic Memory for LLM Agents",
            "url": "https://arxiv.org/abs/2502.12110v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Zujie Liang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "A-MEM: Agentic Memory for LLM Agents",
            "url": "https://arxiv.org/abs/2502.12110v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Kai Mei",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "A-MEM: Agentic Memory for LLM Agents",
            "url": "https://arxiv.org/abs/2502.12110v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Hang Gao",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "A-MEM: Agentic Memory for LLM Agents",
            "url": "https://arxiv.org/abs/2502.12110v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Juntao Tan",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "A-MEM: Agentic Memory for LLM Agents",
            "url": "https://arxiv.org/abs/2502.12110v1"
          }
        },
        {
          "attribution_basis": "SOURCE_CITED",
          "credit": "historical_scientific",
          "entity_kind": "historical_person",
          "name": "Yongfeng Zhang",
          "note": "Archive attribution; detailed role assignment remains source-bound",
          "roles": [
            "formulator"
          ],
          "source": {
            "citation": "A-MEM: Agentic Memory for LLM Agents",
            "url": "https://arxiv.org/abs/2502.12110v1"
          }
        }
      ],
      "evidence": [
        {
          "description": "Bibliographic/stated-result source; not a WRS proof verification",
          "id": "source-0",
          "kind": "source_reference",
          "source": {
            "citation": "A-MEM: Agentic Memory for LLM Agents",
            "url": "https://arxiv.org/abs/2502.12110v1"
          }
        }
      ],
      "origin": "HUMAN_LEGACY",
      "record_profile": "wrs-local-research-notes-0.1",
      "record_type": "research_note",
      "rrp_version": "0.1",
      "scope": {
        "description": "Generated relationships and descriptions are model outputs, not verified facts or causal links. Defined prompts and retrieval limits remain part of the workflow. Different models and question categories have mixed results, and lower retrieved-token counts exclude all writing and updating costs. Its original table and another paper’s quotation swap two category labels; those cross-paper category comparisons remain unresolved. Original-version authors and affiliations are retained rather than replaced by a later conference revision.",
        "domain": "External agent memory"
      },
      "sources": [
        {
          "citation": "A-MEM: Agentic Memory for LLM Agents",
          "url": "https://arxiv.org/abs/2502.12110v1"
        }
      ],
      "statement": "# A-Mem: connecting and revising notes for an agent\n\nUseful information is not always found by searching for the exact words used when it was stored. A-Mem turns incoming experiences into notes with keywords, tags, contextual descriptions and embeddings. The system finds related notes, creates links and can revise earlier descriptions as new information arrives. Xu and colleagues test this linked-note design across several language models on conversational-memory tasks. The contribution is the specific agent memory construction and evolution method, inspired by human linked-note practices rather than inventing those practices.\n\n## Scientific scope\n\nGenerated relationships and descriptions are model outputs, not verified facts or causal links. Defined prompts and retrieval limits remain part of the workflow. Different models and question categories have mixed results, and lower retrieved-token counts exclude all writing and updating costs. Its original table and another paper’s quotation swap two category labels; those cross-paper category comparisons remain unresolved. Original-version authors and affiliations are retained rather than replaced by a later conference revision.\n\n## Reading status\n\nThis is a source-linked WRS catalogue note. A full explanatory guide and independent scientific reconstruction have not been completed for this entry. Read the identified original work for its complete narrative and arguments.\n\n## People and systems\n\nWujiang Xu; Zujie Liang; Kai Mei; Hang Gao; Juntao Tan; Yongfeng Zhang\n\nSource-listed human researchers and engineers for the exact method or resource. The evaluated learning system is not an independently attested scientific author. Earlier methods, funding and data-collection roles remain separate. Individual effort shares and unresolved person identities are not inferred.\n\n\n\n## Original sources\n\n- [A-MEM: Agentic Memory for LLM Agents](https://arxiv.org/abs/2502.12110v1)\n",
      "summary": "Useful information is not always found by searching for the exact words used when it was stored. A-Mem turns incoming experiences into notes with keywords, tags, contextual descriptions and embeddings. The system finds related notes, creates links and can revise earlier descriptions as new information arrives. Xu and colleagues test this linked-note design across several language models on conversational-memory tasks. The contribution is the specific agent memory construction and evolution method, inspired by human linked-note practices rather than inventing those practices.",
      "title": "A-Mem: connecting and revising notes for an agent"
    },
    "record_id": "urn:uuid:52a6a569-7bd2-462d-a558-b43f6d1cabf7",
    "version": 1,
    "source_ref": {
      "record_id": "urn:uuid:52a6a569-7bd2-462d-a558-b43f6d1cabf7",
      "version": 1,
      "content_hash": "sha256:0548def1521e919c5df3629f31b4ab008bd51330f699626ba6d3f364d19ba645"
    },
    "export_view": "wrs-public-editorial-view-1",
    "public_view_hash": "sha256:abf389e38abee84d63e87c9aaa7606092652b456b586130492a5299a80dcb3e7"
  },
  "target": {
    "record_id": "urn:uuid:52a6a569-7bd2-462d-a558-b43f6d1cabf7",
    "version": 1,
    "content_hash": "sha256:0548def1521e919c5df3629f31b4ab008bd51330f699626ba6d3f364d19ba645"
  },
  "published_grade": {
    "profile": "wrs-published-grade-1",
    "edition": "2026-10-28.1",
    "id": "xu-et-al-amem-linked-evolving-memory-notes-2025",
    "entry_id": "xu-et-al-amem-linked-evolving-memory-notes-2025",
    "revision": 1,
    "title": "A-Mem: connecting and revising notes for an agent",
    "context": "External agent memory",
    "track": "Reusable scientific method, experimental result or historical framework",
    "band": "B",
    "modifier": "+",
    "status": "PROVISIONAL_EDITORIAL",
    "assessed_on": "2026-10-23",
    "evidence_cutoff": "2026-10-23",
    "achievement_state": "SUPPORTED_SCOPED_RESULT",
    "what_changed": "Useful information is not always found by searching for the exact words used when it was stored. A-Mem turns incoming experiences into notes with keywords, tags, contextual descriptions and embeddings. The system finds related notes, creates links and can revise earlier descriptions as new information arrives. Xu and colleagues test this linked-note design across several language models on conversational-memory tasks. The contribution is the specific agent memory construction and evolution method, inspired by human linked-note practices rather than inventing those practices.",
    "scope": "Useful information is not always found by searching for the exact words used when it was stored. A-Mem turns incoming experiences into notes with keywords, tags, contextual descriptions and embeddings. The system finds related notes, creates links and can revise earlier descriptions as new information arrives. Xu and colleagues test this linked-note design across several language models on conversational-memory tasks. The contribution is the specific agent memory construction and evolution method, inspired by human linked-note practices rather than inventing those practices. Generated relationships and descriptions are model outputs, not verified facts or causal links. Defined prompts and retrieval limits remain part of the workflow. Different models and question categories have mixed results, and lower retrieved-token counts exclude all writing and updating costs. Its original table and another paper’s quotation swap two category labels; those cross-paper category comparisons remain unresolved. Original-version authors and affiliations are retained rather than replaced by a later conference revision.",
    "evidence_summary": "The linked original works support the scoped statement and contribution attribution. WRS has not independently replayed experiments or reconstructed a full mathematical proof. Generated relationships and descriptions are model outputs, not verified facts or causal links. Defined prompts and retrieval limits remain part of the workflow. Different models and question categories have mixed results, and lower retrieved-token counts exclude all writing and updating costs. Its original table and another paper’s quotation swap two category labels; those cross-paper category comparisons remain unresolved. Original-version authors and affiliations are retained rather than replaced by a later conference revision.",
    "references": [
      {
        "title": "A-MEM: Agentic Memory for LLM Agents",
        "url": "https://arxiv.org/abs/2502.12110v1",
        "locator": "Original scoped contribution, statement/method and evidence limits; source-specific attribution retained."
      }
    ],
    "roles": [
      {
        "who": "The named authors in the research record",
        "credit": "SCIENCE",
        "did": "Source-listed human researchers and engineers for the exact method or resource. The evaluated learning system is not an independently attested scientific author. Earlier methods, funding and data-collection roles remain separate. Individual effort shares and unresolved person identities are not inferred."
      }
    ],
    "target": {
      "record_id": "urn:uuid:52a6a569-7bd2-462d-a558-b43f6d1cabf7",
      "version": 1,
      "content_hash": "sha256:0548def1521e919c5df3629f31b4ab008bd51330f699626ba6d3f364d19ba645"
    },
    "scientific_correctness_certified": false,
    "independent_expert_calibration": false,
    "method": "PROPRIETARY",
    "points": "45000"
  },
  "canonical_agent_submission": false,
  "scientific_verification_awarded": false,
  "reader_guide": null,
  "reading_status": "SOURCE_LINKED_NOTE"
}