SATE-Bench评测主动空间推理
AI 总结
论文《Humans in Space》于2026年10月25日提交至arXiv,提出包含316个真实场景和2,525组多轮问答的交互式基准SATE-Bench。该基准通过带步数惩罚的效率奖励,评估多模态大模型能否主动查询相邻视角,以获取被遮挡的视觉证据。作者报告称,受测模型常在高置信度下过早停止探索;GRPO微调虽提高了探索程度,却因过度探索和难以融合多视角上下文而降低总体准确率。
深度见解
SATE-Bench为检验多模态大模型能否通过主动观察获取证据、而非只依赖被动多视角感知,提供了具体评测方法。
Computer Science > Computer Vision and Pattern Recognition
arXiv:2610.34149 (cs)
[Submitted on 25 Oct 2026]
Title:Humans in Space: Can MLLMs Construct Human-Centric Spatial Understanding via Active Exocentric Exploration?
Authors:Tianchen Guo, Tengyue Zhang, Chen Liu, Ling Chen, Xin Yu
View a PDF of the paper titled Humans in Space: Can MLLMs Construct Human-Centric Spatial Understanding via Active Exocentric Exploration?, by Tianchen Guo and 4 other authors
#SATE-Bench#Multimodal Large Language Models#Group Relative Policy Optimization