MMEnterprise-Bench: Evaluating Enterprise Agents over Evolving Multimodal Records
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:...
| Authors | Seohyun Lee, Jongha Kim, Dohwan Ko et al. |
|---|---|
| Primary category | cs.AI |
| Published | 20 October 2026 |
| Last updated at source | 20 October 2026 |
Recent changes
- 21 Oct 2026 Description: 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 → 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
- 21 Oct 2026 Topics added cs.AI removed hf-daily-papers, multimodal llms, evidence reasoning, conflict resolution, unanswerability, cross-source conflicts, temporal conflicts, retrieval budget, mmenterprise-bench
Changes detected by Silytics between refreshes of the source.
Silytics shows public metadata from arXiv and links to the original. Information may be incomplete or out of date. Last refreshed 21 October 2026. Licenses and terms of the original apply to the work itself. Not financial, legal or professional advice.