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

TL;DR

This paper presents a training-free framework for building private-domain multi-agent conversational systems by using behavior modeling and documentation, enabling scalable adaptation without retraining.

Contribution

It introduces a novel, training-free approach that leverages structured specifications and domain instructions for private multi-agent systems, avoiding fine-tuning and synthetic data generation.

Findings

Supports lightweight deployment of multi-agent systems

Leverages API specifications as retrieval resources

Enables synthetic dialogue generation for evaluation

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.