Controlling Collectives of AI Agents in Reasoning Space with Spatial Transformers

2026-09-23

AI Summary

为解决大型多机器人任务中的控制问题，提出COMPASS架构，利用空间变换器生成本地反馈，实现对大量智能机器人的有效控制。

Abstract

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 the input command, which can cancel biases; an advantage that is held across scale. Compared against a centralized frontier LLM policy and a language-only communication ablation, we find that the coupled design of COMPASS decisively produces cohesive flocking formations that accurately fly the commanded intent. We show that reasoning feedback works best when composed with a compact learned token. Our ablations show that hand engineered feedback with raw state appearing in the language channel obliterates cohesion. COMPASS generalizes zero-shot to unseen instructions of ambiguous meaning while commanding flocks up to 16 times its training scale, flying up to 1024 robots under natural language commands.

Problem

• Large Language Models
• multi-robot tasks
• scalable control
• natural language commands
• collective robotics

Innovation

• Spatial Transformers
• Feedback Control
• Multi-robot Systems
• Scalability
• Natural Language Commands