Metraipolis › archive › dc_027bef46da7f

One Assistant, Many Memories: Benchmarking Real-World Group Assistance When Recall Is Not Enough — arXiv:2611.04867

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.04867
License (as archived)
CC0-1.0
Archived
2026-11-04T18:37:19.168Z
SHA-256 of the archived text
8112da0197b04baee5592e33a9985187ee330de5757223757399cdfb0e0de37f
Stable URL of this page
https://metraipolis.com/documento/dc_027bef46da7f

How to cite

One Assistant, Many Memories: Benchmarking Real-World Group Assistance When Recall Is Not Enough — arXiv:2611.04867 — arXiv (en), https://arxiv.org/abs/2611.04867 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_027bef46da7f (Metraipolis archive dc_027bef46da7f, sha256 8112da0197b04baee5592e33a9985187ee330de5757223757399cdfb0e0de37f)
BibTeX
@misc{dc027bef46da7f,
  title = {One Assistant, Many Memories: Benchmarking Real-World Group Assistance When Recall Is Not Enough — arXiv:2611.04867},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.04867},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_027bef46da7f; sha256 8112da0197b04baee5592e33a9985187ee330de5757223757399cdfb0e0de37f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.04867. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The value of memory lies not only in recall but in using it to provide appropriate assistance. Recent benchmarks test memory use in personalisation and agentic tasks, but seldom evaluate assistance without fixed answers or integration across multiple participants. Group chats make both challenges more acute: an assistant must integrate information from multiple members, track revisions and conflicts over time, and produce one response for the group. Yet existing group memory benchmarks rely on synthetic conversations and inherit constrained evaluation from general memory benchmarks, focusing on recall against fixed answers or decisions over a closed set. We introduce GroupAssistBench, the first memory benchmark from real-world group conversations with a deployed group assistant, covering 80,299 messages in 50 groups and costing over $53K. Over the same histories, GroupAssistBench evaluates memory recall (L1) with reference answers and memory use (L2) with service requests without fixed answers across single, distributed, and conflicting memories (M1--M3). Requests are verified to require group history, memories are anchored to their sources, and L2 uses tailored rubrics with penalties derived from real user feedback. Across evaluations of frontier models with full context, retrieval methods, and memory systems, the strongest memory system rivals full context on recall but falls far behind on use, especially for distributed and conflicting memories. Together, two additions that relate retrieved memories and bind remembered facts as response constraints bring consistent gains, showing that group memory systems must improve use, not recall alone.

Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno).
Categorie arXiv: Computation and Language (cs.CL) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2611.04867 — 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 2026-11-04T18:32:37.469Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).