Metraipolis › archive › dc_a0d0adcba2be
ColaBench: Evaluating Memory-Guided Knowledge Acquisition in Personal Agents — arXiv:2610.30989
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.30989
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-23T15:13:08.954Z
- SHA-256 of the archived text
b99a0ee673edcda0d73fc974b487f8700f57a4b6d017ac44d573fc862082ece9- Stable URL of this page
https://metraipolis.com/documento/dc_a0d0adcba2be
How to cite
ColaBench: Evaluating Memory-Guided Knowledge Acquisition in Personal Agents — arXiv:2610.30989 — arXiv (en), https://arxiv.org/abs/2610.30989 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_a0d0adcba2be (Metraipolis archive dc_a0d0adcba2be, sha256 b99a0ee673edcda0d73fc974b487f8700f57a4b6d017ac44d573fc862082ece9)
BibTeX
@misc{dca0d0adcba2be,
title = {ColaBench: Evaluating Memory-Guided Knowledge Acquisition in Personal Agents — arXiv:2610.30989},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.30989},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_a0d0adcba2be; sha256 b99a0ee673edcda0d73fc974b487f8700f57a4b6d017ac44d573fc862082ece9},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.30989. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Personal agents need to draw on long-term interaction history to retrieve and apply external knowledge suited to a user's current request. Even an answer grounded in relevant documents can be unsuitable when it overlooks the user's circumstances. This creates two connected challenges: using historical conditions to identify the knowledge needed for a new request, and applying that knowledge to the user's situation. Existing benchmarks advance memory recall, personalized retrieval, and memory-guided action, while the joint evaluation of these two challenges remains underexplored. We introduce ColaBench, a synthetic benchmark in health and daily living, with 349 tasks across 10 Profiles and a knowledge base of 13,033 documents. Its Evidence Graph connects personal conditions to their disclosures across public interaction sessions, records prior document exposure, and links answer requirements to personal and newly acquired document evidence. We also introduce MemKB, which uses state summaries to inform queries and rule application, and memory-document links to retrieve knowledge associated with the user's history. MemKB achieves 86.25% Accuracy with an average of 4.07 interaction rounds per task. Task-level analysis finds larger gains on tasks integrating information across multiple historical Facts; error analysis further identifies unsupported personal assumptions and rule misapplication as obstacles to using retrieved evidence. ColaBench provides traceable tasks and an evaluation framework for studying how memory guides knowledge acquisition and rule application. 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/2610.30989 — 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 2026-10-23T15:09:08.418Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).