Navigating Motion Agents in Dynamic and Cluttered Environments through LLM Reasoning
It addresses the challenge of autonomous navigation for AI agents in complex real-world settings, representing an incremental improvement over earlier studies.
This paper tackles the problem of enabling motion agents powered by large language models (LLMs) to navigate autonomously in dynamic and cluttered environments, overcoming prior limitations by supporting multi-agent coordination and dynamic obstacle avoidance without retraining.
This paper advances motion agents empowered by large language models (LLMs) toward autonomous navigation in dynamic and cluttered environments, significantly surpassing first and recent seminal but limited studies on LLM's spatial reasoning, where movements are restricted in four directions in simple, static environments in the presence of only single agents much less multiple agents. Specifically, we investigate LLMs as spatial reasoners to overcome these limitations by uniformly encoding environments (e.g., real indoor floorplans), agents which can be dynamic obstacles and their paths as discrete tokens akin to language tokens. Our training-free framework supports multi-agent coordination, closed-loop replanning, and dynamic obstacle avoidance without retraining or fine-tuning. We show that LLMs can generalize across agents, tasks, and environments using only text-based interactions, opening new possibilities for semantically grounded, interactive navigation in both simulation and embodied systems.