multimodal-context

标签

Cards List
#multimodal-context

Screenshots or Tools? Eliciting Tool Use and Managing Multimodal Context in Hybrid GUI-MCP Computer-Use Agents

arXiv cs.AI ↗ · 2026-08-05 缓存

This paper investigates when hybrid computer-use agents actually choose to use MCP tools versus screenshots, finding that tool availability alone does not guarantee adoption: a reasoning model improves while a non-reasoning model degrades. It also explores training and context compression strategies to close the adoption gap and reduce token costs.

0 人收藏 0 人点赞
← 返回首页

提交意见反馈