---
id: 20260618-T0-16
title: "Can Agents Read the Room？首个测试多模态社交智能的基准"
title_en: "Can Agents Read the Room? First Benchmark for Multimodal Social Intelligence"
url: https://ai.daily.yangsir.net/daily/20260618-T0-16
issue_date: 2026-06-18
publish_date: 2026-06-17T04:00:00.000Z
category: research
source_name: "arXiv cs.CL (NLP)"
source_url: https://arxiv.org/abs/2606.15152
---

# Can Agents Read the Room？首个测试多模态社交智能的基准

研究者推出首个评估多模态代理社交智能的基准测试，聚焦于AI理解面部表情、姿态、眼神等社交信号的能力。现有社交代理评测大多基于文本，忽视了关键的非语言社交线索。该基准通过模拟环境测试AI能否正确解读视觉社交信号，填补了评测空白。

## English Version

**Can Agents Read the Room? First Benchmark for Multimodal Social Intelligence**

Researchers introduced the first benchmark for evaluating multimodal agents' social intelligence, focusing on their ability to understand facial expressions, posture, gaze, and other visual social signals. Existing social agent benchmarks are primarily text-based, overlooking crucial non-verbal social cues. This benchmark tests whether multimodal agents can correctly interpret visual social signals in simulated environments, addressing a significant gap in AI evaluation.

---

**来源**：[arXiv cs.CL (NLP)](https://arxiv.org/abs/2606.15152)

**详情页**：https://ai.daily.yangsir.net/daily/20260618-T0-16

---

*智语观潮 · Daily — https://ai.daily.yangsir.net/llms.txt*