AIIC AI Intelligence Centre

SOURCE-LINKED INTELLIGENCE

EviSeek: An Evidence-Centric Agentic Framework for Embodied Active Information Seeking

arXiv · AI, language, vision and robotics · article · Nov 4, 2026 · UTC

Active embodied question answering requires agents to acquire evidence through viewpoint changes and physical interaction. The central challenge is to avoid undirected interaction: taking plausible actions without specifying what evidence they should reveal for answering the question. Action plans and accumulated histories alone can leave the informational purpose of an interaction implicit. We introduce EviSeek, a training-free framework that makes question-derived evidence demands explicit acquisition objectives, linking observation-conditioned actions and selectively retained evidence to th

Read original source ↗ Open in workspace

recordType
paper
region
Global

Evidence & attribution

First collected: 2026-11-05T14:44:11.081Z. This is not the publication date.