CloneMem: Benchmarking Long-Term Memory for AI Clones
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915722461970432 |
|---|---|
| author | Hu, Sen Zhang, Zhiyu Wei, Yuxiang Han, Xueran Tang, Zhenheng Wang, Huacan Chen, Ronghao |
| author_facet | Hu, Sen Zhang, Zhiyu Wei, Yuxiang Han, Xueran Tang, Zhenheng Wang, Huacan Chen, Ronghao |
| contents | AI Clones aim to simulate an individual's 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's 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 |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2601_07023 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | CloneMem: Benchmarking Long-Term Memory for AI Clones Hu, Sen Zhang, Zhiyu Wei, Yuxiang Han, Xueran Tang, Zhenheng Wang, Huacan Chen, Ronghao Artificial Intelligence AI Clones aim to simulate an individual's 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's 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 |
| title | CloneMem: Benchmarking Long-Term Memory for AI Clones |
| topic | Artificial Intelligence |
| url | https://arxiv.org/abs/2601.07023 |