# CUSP: Decomposable Collective Uncertainty for Multi-Agent Multimodal Reasoning

> *Машинный перевод (AI-generated content)*

**Published:** 9 сентября 2026 г.
**Author:** Chung-En Johnny Yu, David Garcia, Brian Jalaian, Nathaniel D. Bastian
**Source:** arXiv — cs.AI
**Language:** ru-RU
**HTML:** https://aiqazaqstan.com/ru/articles/cusp-decomposable-collective-uncertainty-for-multi-agent-multimodal-reas

arXiv:2609.05708v1 Announce Type: new Abstract: Aggregating heterogeneous vision-language models (VLMs) can improve multimodal reasoning, but neither an individual model's confidence nor that of the aggregated answer measures reliability at the system level. We present CUSP…

> Материал агрегирован из первоисточника: **arXiv — cs.AI**
> [Читать полностью в arXiv — cs.AI](https://arxiv.org/abs/2609.05708)

**Теги:** #arXiv

---

*AI Qazaqstan — non-commercial informational portal about AI in Kazakhstan. Machine translations and summaries are AI-generated.*