SOURCE-LINKED INTELLIGENCE

Speak for Me: Giving LLMs the Situational Awareness to Participate in a Meeting

arXiv · AI, language, vision and robotics · article · Sep 3, 2026 · UTC

In online meeting delegation, LLM agents fail to recognize when to speak. With no structured way to track stances, coverage, and floor, they miss the moments where they should contribute. Prompt-only delegates stay silent on 51.4% of the absent participant's talking opportunities on the AMI corpus. We present CAPA (Collaborative Agent Predictive Architecture), an architecture for online meeting delegation. A Perceiver updates the meeting state from each observed turn. A Predictor forecasts how the conversation will continue. A Controller decides whether to speak and which proposition to surfac

Read original source ↗ Open in workspace

recordType

paper

region

Global