The rise of agentic systems that combine orchestration, tool use, and conversational capabilities, has been more visible by the recent advent of large language models (LLMs). While open-domain frameworks exist, applying them in private domains remains difficult due to heterogeneous tool formats, domain-specific jargon, restricted accessibility of APIs, and complex governance. Conventional solutions, such as fine-tuning on synthetic dialogue data, are burdensome and brittle under domain shifts, and risk degrading general performance. In this light, we introduce a framework for constructing private-domain tool-calling multi-agent systems that does not necessitate data generation and model tuning, by modeling user and system behaviors via tool-use documentation. With a simplified composition that assumes an orchestrator, a tool-calling agent, and a general chat agent, we show that the proposed approach enables scalable adaptation to private tools, which had been previously achieved by accompanying continual retraining. Our framework supports practical use cases, including lightweight deployment of in-house multi-agent systems, providing a sustainable method for aligning agent behavior with domain expertise in private, enterprise-level conversational ecosystems.

翻译：暂无翻译