Z-Space: A Multi-Agent Tool Orchestration Framework for Enterprise-Grade LLM Automation

TL;DR

Z-Space is a multi-agent framework that improves enterprise LLM automation by accurately matching tools to user intents, reducing token usage, and increasing invocation accuracy in complex multi-step tasks.

Contribution

The paper introduces Z-Space, a novel multi-agent tool invocation framework with a structured semantic understanding and a new tool filtering algorithm, enhancing efficiency and accuracy in large-scale enterprise LLM applications.

Findings

Reduced average token consumption by 96.26%

Achieved 92% tool invocation accuracy

Deployed successfully in large-scale enterprise scenarios

Abstract

Large Language Models can break through knowledge and timeliness limitations by invoking external tools within the Model Context Protocol framework to achieve automated execution of complex tasks. However, with the rapid growth of enterprise-scale MCP services, efficiently and accurately matching target functionalities among thousands of heterogeneous tools has become a core challenge restricting system practicality. Existing approaches generally rely on full-prompt injection or static semantic retrieval, facing issues including semantic disconnection between user queries and tool descriptions, context inflation in LLM input, and high inference latency. To address these challenges, this paper proposes Z-Space, a data-generation-oriented multi-agent collaborative tool invocation framework Z-Space. The Z-Space framework establishes a multi-agent collaborative architecture and tool filtering algorithm: (1) A structured semantic understanding of user queries is achieved through an intent parsing model; (2) A tool filtering module (FSWW) based on fused subspace weighted algorithm realizes fine-grained semantic alignment between intents and tools without parameter tuning; (3) An inference execution agent is constructed to support dynamic planning and fault-tolerant execution for multi-step tasks. This framework has been deployed in the Eleme platform's technical division, serving large-scale test data generation scenarios across multiple business units including Taotian, Gaode, and Hema. Production data demonstrates that the system reduces average token consumption in tool inference by 96.26\% while achieving a 92\% tool invocation accuracy rate, significantly enhancing the efficiency and reliability of intelligent test data generation systems.