English

Behavior Modeling for Training-free Building of Private Domain Multi Agent System

Multiagent Systems 2025-11-14 v1

Abstract

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 private-domain multi-agent conversational systems that avoids training and data generation by adopting behavior modeling and documentation. Our design simply assumes an orchestrator, a tool-calling agent, and a general chat agent, with tool integration defined through structured specifications and domain-informed instructions. This approach enables scalable adaptation to private tools and evolving contexts without continual retraining. The framework supports practical use cases, including lightweight deployment of multi-agent systems, leveraging API specifications as retrieval resources, and generating synthetic dialogue for evaluation -- providing a sustainable method for aligning agent behavior with domain expertise in private conversational ecosystems.

Keywords

Cite

@article{arxiv.2511.10283,
  title  = {Behavior Modeling for Training-free Building of Private Domain Multi Agent System},
  author = {Won Ik Cho and Woonghee Han and Kyung Seo Ki and Young Min Kim},
  journal= {arXiv preprint arXiv:2511.10283},
  year   = {2025}
}

Comments

10 pages, 1 figure, 2 tables