SOURCE-LINKED INTELLIGENCE

Controlling Collectives of AI Agents in Reasoning Space with Spatial Transformers

arXiv · AI, language, vision and robotics · article · Sep 23, 2026 · UTC

Large Language Models (LLMs) introduce an exciting new paradigm for planning and navigation in robotics, but fail on even simple multi-robot tasks as team sizes grow. We propose COMPASS, a scalable, decentralized multi-robot architecture for controlling large collectives of agentic robots with reasoning space feedback control. Feedback is generated locally on each robot by a spatial transformer which aggregates multi-hop messages across the fleet into a learned feedback token. Our experiments find that collectives of language models demonstrate performance gains from structured diversity of th

Read original source ↗ Open in workspace

recordType

paper

region

Global