{
  "annotation_id": "86b6a0ac-4c0f-49ad-ada6-ead54886469b",
  "date_created": "2026-02-17T05:53:08.754000Z",
  "date_modified": "2026-02-17T05:53:08.754000Z",
  "file_hash": "d722dc8227093f04261d2762d22cd168751365be24c1d7ae846ec37506b7715c",
  "private": false,
  "record": {
    "abstract": "AI Clones aim to simulate an individual\u0027s thoughts and behaviors to enable long-term, personalized interaction, placing stringent demands on memory systems to model experiences, emotions, and opinions over time. Existing memory benchmarks primarily rely on user-agent conversational histories, which are temporally fragmented and insufficient for capturing continuous life trajectories. We introduce CloneMem, a benchmark for evaluating longterm memory in AI Clone scenarios grounded in non-conversational digital traces, including diaries, social media posts, and emails, spanning one to three years. CloneMem adopts a hierarchical data construction framework to ensure longitudinal coherence and defines tasks that assess an agent\u0027s ability to track evolving personal states. Experiments show that current memory mechanisms struggle in this setting, highlighting open challenges for life-grounded personalized AI. Code and dataset are available at https://github.com/AvatarMemory/CloneMemBench",
    "arxiv_id": "2601.07023",
    "authors": [
      "Sen Hu",
      "Zhiyu Zhang",
      "Yuxiang Wei",
      "Xueran Han",
      "Zhenheng Tang",
      "Huacan Wang",
      "Ronghao Chen"
    ],
    "categories": [
      "cs.AI"
    ],
    "license": "http://arxiv.org/licenses/nonexclusive-distrib/1.0/",
    "title": "CloneMem: Benchmarking Long-Term Memory for AI Clones",
    "url": "https://arxiv.org/abs/2601.07023",
    "version": "v1"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "add54f11-65d6-4cdc-9b97-87d52a244122",
    "id": "arXiv Dataset",
    "type": "Model",
    "variant": "snapshot-2026-01-17",
    "version": "0.1.0"
  },
  "user_id": 1000002
}