AssemPlanner: A Multi-Agent Based Task Planning Framework for Flexible Assembly System

2026-05-09

AI Summary

This work addresses the challenges in flexible assembly systems where new production line configurations rely heavily on multidisciplinary experts and involve time-consuming task planning. To overcome these limitations, the authors propose a multi-agent adaptive task planning framework that leverages a central scheduling agent (SchedAgent) integrated with ReAct reasoning to coordinate a knowledge agent (KnowledgeAgent) and a line balancing agent (LineBalanceAgent). This framework automatically translates natural language task descriptions into executable operation sequences that satisfy complex industrial constraints, while incorporating environmental feedback through scene graphs. By moving beyond traditional static assembly lines, the approach enables dynamic, autonomous decision-making. The complete implementation, including code and datasets, has been open-sourced to facilitate reproducibility and further extension.

Abstract

In flexible assembly systems, existing task planning methods require a time-consuming configuration process by multiple experts to establish a production line for a new product. To address this challenge, we propose a multi-agent based task planning framework for flexible assembly systems, denoted as AssemPlanner. It takes tasks described in natural language as input, which are then converted into actionable sequential production operations. It comprises several specialized agents, including SchedAgent , KnowledgeAgent, LineBalanceAgent, and a scene graph. Within the proposed framework, SchedAgent serves as the central reasoning engine. Departing from traditional static pipelines, AssemPlanner utilizes a ReAct-based SchedAgent to adaptively adjust actions via multi-agent feedback. By observing the feedback from KnowledgeAgent, LineBalanceAgent, and the scene graph, it autonomously resolves complex industrial process constraints. To facilitate reproducibility, all code and datasets are released at https://github.com/chz332/Assemplanner.

Problem

• flexible assembly systems
• task planning
• production line configuration
• expert-dependent setup
• time-consuming configuration

Innovation

• multi-agent system
• task planning
• flexible assembly
• ReAct-based reasoning
• natural language to action