Hybrid LLM-based Intelligent Framework for Robot Task Scheduling

2026-05-15

AI Summary

This study addresses the inefficiencies, suboptimal resource utilization, and poor dynamic adaptability commonly observed in construction robot task scheduling. To overcome these challenges, the authors propose an intelligent scheduling framework leveraging large language models (LLMs). The framework employs a natural language interface to interpret task objectives and robot capabilities, and introduces an innovative generator–supervisor dual-LLM mechanism—utilizing GPT-4 as the generator and Gemma 3, Llama 4, or Mistral 7B as the supervisor—integrated with a multi-agent cooperative scheduling algorithm. This architecture enables efficient, real-time, and adaptive task planning. Experimental results demonstrate that the proposed approach significantly improves scheduling efficiency and resource utilization, thereby validating the effectiveness and practical utility of LLMs in construction robot task scheduling.

Abstract

This study introduces intelligent frameworks that use Large Language Models (LLMs) to improve task scheduling for construction robots. The LLM is fed with key data about the desired task, such as agent action abilities, and the desired end goal to be achieved. A well-balanced allocation strategy is developed, optimizing both time efficiency and resource utilization. Our system utilizes a Natural Language Processing interface to streamline communication with construction professionals and adapt in real-time to unexpected site conditions. We concurrently use two LLM agents, specifically generator (GPT-4) and supervisor (Gemma 3/Llama 4/Mistral 7b) LLM agents to provide a more precise task schedule. We evaluate the proposed methodology using a straightforward scenario and provide metric scores to prove the efficacy of the frameworks. Our results highlight that the implementation of LLMs is crucial in construction operational tasks including robots.

Problem

• Robot Task Scheduling
• Large Language Models
• Construction Automation
• Intelligent Framework
• Resource Allocation

Innovation

• Large Language Models
• Robot Task Scheduling
• Hybrid LLM Agents
• Natural Language Interface
• Construction Automation