Metraipolis › archive › dc_6bf193473aff
Why Bother Me Again? Benchmarking Personal Agent Memory for Interaction Preferences — arXiv:2610.30485
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.30485
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-25T08:32:24.324Z
- SHA-256 of the archived text
47ec322d1a69275e5b0f644231c375d75f8b581704add965f1c21f03f0443497- Stable URL of this page
https://metraipolis.com/documento/dc_6bf193473aff
How to cite
Why Bother Me Again? Benchmarking Personal Agent Memory for Interaction Preferences — arXiv:2610.30485 — arXiv (en), https://arxiv.org/abs/2610.30485 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6bf193473aff (Metraipolis archive dc_6bf193473aff, sha256 47ec322d1a69275e5b0f644231c375d75f8b581704add965f1c21f03f0443497)
BibTeX
@misc{dc6bf193473aff,
title = {Why Bother Me Again? Benchmarking Personal Agent Memory for Interaction Preferences — arXiv:2610.30485},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.30485},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6bf193473aff; sha256 47ec322d1a69275e5b0f644231c375d75f8b581704add965f1c21f03f0443497},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30485. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Personal intelligence systems are taking on increasingly complex everyday tasks, yet repeated questions, unnecessary confirmations, and unwanted outreach can turn capable assistance into interaction burden. Reducing this burden requires agents to remember how users want to be assisted. However, existing memory benchmarks focus on factual recall and personalized answers and rarely test how agents learn and act on interaction preferences. We introduce MemPABench, an interactive environment for on-policy evaluation of memory in personal agents. MemPABench poses long-horizon tasks requiring agents to decide when to clarify, confirm, or act autonomously. Four grounded simulated users hold 14 preferences across work and personal contexts. Their feedback spans 99 sessions over four months, with five event-driven changes per user testing memory updates. We evaluate preference selection, delivered behavior, and sensitivity to context and preference change. Evaluating four memory systems across four LLM backbones, we find that current memory brings limited gains in preference selection. Retrieval-based systems (i.e. Mem0, MemOS, simple RAG) do not outperform No Memory, while File-based memory improves accuracy but applies preferences beyond relevant contexts. Our analysis shows that current memory struggles to retrieve interaction preferences and adapt to preference changes. Even with the correct preference available, overriding the agent's default interaction habits remains challenging. The environment and dataset are available at this https URL . Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Artificial Intelligence (cs.AI) ; Computation and Language (cs.CL). Pagina del lavoro: https://arxiv.org/abs/2610.30485 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-25T08:31:12.991Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).