Metraipolis › archive › dc_f47bbd15c56b

MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records — arXiv:2610.27911

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.27911
License (as archived)
CC0-1.0
Archived
2026-10-21T07:06:54.988Z
SHA-256 of the archived text
77fdf0adca2e2c490df7971bbfb9799cf11a5a47d396ab7a0c86dd7bf416444f
Stable URL of this page
https://metraipolis.com/documento/dc_f47bbd15c56b

How to cite

MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records — arXiv:2610.27911 — arXiv (en), https://arxiv.org/abs/2610.27911 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_f47bbd15c56b (Metraipolis archive dc_f47bbd15c56b, sha256 77fdf0adca2e2c490df7971bbfb9799cf11a5a47d396ab7a0c86dd7bf416444f)
BibTeX
@misc{dcf47bbd15c56b,
  title = {MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records — arXiv:2610.27911},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.27911},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_f47bbd15c56b; sha256 77fdf0adca2e2c490df7971bbfb9799cf11a5a47d396ab7a0c86dd7bf416444f},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.27911. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Enterprise agents answer questions over workplace records that evolve through team collaboration. As information is shared, corrected, and revised across documents, chats, and figures, multiple versions of the same information accumulate in the workspace. Reliable question answering therefore requires agents to reason over sufficient evidence, resolve cross-source and temporal conflicts, and recognize when the available evidence is insufficient to establish an answer. To systematically evaluate these capabilities, we introduce MMEnterprise-Bench, a benchmark comprising 1,613 questions grounded in evolving multimodal records from simulated collaboration projects, covering three categories: Evidence Reasoning, Conflict Resolution, and Unanswerability. We evaluate 10 proprietary and open-source multimodal LLMs and find that even the strongest models struggle when evidence contains cross-source or temporal conflicts or spans multiple images. Moreover, increasing the retrieval budget or employing a larger retriever improves evidence recall but does not consistently translate into higher answer accuracy. These findings highlight the persistent challenges of reasoning over evolving workplace records and establish MMEnterprise-Bench as a testbed for developing more reliable enterprise agents. Code and data 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).
Pagina del lavoro: https://arxiv.org/abs/2610.27911 — 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 2026-10-21T07:05:43.453Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).