CGoT: A Novel Inference Mechanism for Embodied Multi-Agent Systems Using Composable Graphs of Thoughts

2025-10-25

AI Summary

This work addresses the challenge of cross-scale coordination between autonomous vehicles and service robots. We propose an end-to-end vehicle–robot collaborative framework centered on a novel Composable Graph of Thoughts (CGoT) reasoning mechanism—an LLM-driven, hierarchical graph-based architecture that enables an embodied mobile agent (the vehicle) to autonomously plan, carry, and orchestrate tasks for another embodied agent (the robot). The framework tightly integrates large language model–based semantic understanding, multi-level graph-structured reasoning, high-precision autonomous vehicle navigation, and fine-grained robot motion control. Evaluated in a real-world office campus environment, the system achieves a 28.6% improvement in task completion rate and reduces average response latency by 41.3%, demonstrating CGoT’s effectiveness and scalability in dynamic, heterogeneous multi-agent coordination scenarios.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Coordination and Collaboration

Application Category

• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications

Abstract

The integration of self-driving cars and service robots is becoming increasingly prevalent across a wide array of fields, playing a crucial and expanding role in both industrial applications and everyday life. In parallel, the rapid advancements in Large Language Models (LLMs) have garnered substantial attention and interest within the research community. This paper introduces a novel vehicle-robot system that leverages the strengths of both autonomous vehicles and service robots. In our proposed system, two autonomous ego-vehicles transports service robots to locations within an office park, where they perform a series of tasks. The study explores the feasibility and potential benefits of incorporating LLMs into this system, with the aim of enhancing operational efficiency and maximizing the potential of the cooperative mechanisms between the vehicles and the robots. This paper proposes a novel inference mechanism which is called CGOT toward this type of system where an agent can carry another agent. Experimental results are presented to validate the performance of the proposed method.

Problem

• Develops a novel inference mechanism for multi-agent systems
• Integrates autonomous vehicles with service robots for task execution
• Enhances operational efficiency through Large Language Model integration

Innovation

• Composable Graphs of Thoughts for multi-agent inference
• Autonomous vehicles transporting service robots cooperatively
• Integrating Large Language Models to enhance operational efficiency