# Modeling User-System Behavior for Training-free Building of Private Domain Conversational Agents

arXiv: https://arxiv.org/abs/2511.10283 · HTML: https://mlsanity.com/paper/2511.10283/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in General LLM agent frameworks and benchmarks, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 50 references that are in the map.
- First posted on arXiv 13 Nov 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)

## Builds on (most cited first, 24 of 24)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [BioBERT: a pre-trained biomedical language representation model for biomedical text mining](https://mlsanity.com/paper/1901.08746/) (2019)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [Don't Stop Pretraining: Adapt Language Models to Domains and Tasks](https://mlsanity.com/paper/2004.10964/) (2020)
- [Rethinking the Role of Demonstrations: What Makes In-Context Learning Work?](https://mlsanity.com/paper/2202.12837/) (2022)
- [SciBERT: A Pretrained Language Model for Scientific Text](https://mlsanity.com/paper/1903.10676/) (2019)
- [HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face](https://mlsanity.com/paper/2303.17580/) (2023)
- [AgentVerse: Facilitating Multi-Agent Collaboration and Exploring Emergent Behaviors](https://mlsanity.com/paper/2308.10848/) (2023)
- [ToolAlpaca: Generalized Tool Learning for Language Models with 3000 Simulated Cases](https://mlsanity.com/paper/2306.05301/) (2023)
- [Neural Approaches to Conversational AI](https://mlsanity.com/paper/1809.08267/) (2018)
- [Neural Unsupervised Domain Adaptation in NLP---A Survey](https://mlsanity.com/paper/2006.00632/) (2020)
- [Domain Specialization as the Key to Make Large Language Models Disruptive: A Comprehensive Survey](https://mlsanity.com/paper/2305.18703/) (2023)
- [Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark](https://mlsanity.com/paper/2405.08355/) (2024)
- [Injecting Domain-Specific Knowledge into Large Language Models: A Comprehensive Survey](https://mlsanity.com/paper/2502.10708/) (2025)
- [Using Large Language Models to Generate, Validate, and Apply User Intent Taxonomies](https://mlsanity.com/paper/2309.13063/) (2023)
- [ToolDial: Multi-turn Dialogue Generation Method for Tool-Augmented Language Models](https://mlsanity.com/paper/2503.00564/) (2025)
- [A Study on the Implementation of Generative AI Services Using an Enterprise Data-Based LLM Application Architecture](https://mlsanity.com/paper/2309.01105/) (2023)
- [Fine-Tuning Lowers Safety and Disrupts Evaluation Consistency](https://mlsanity.com/paper/2506.17209/) (2025)
- [Building Domain-Specific Machine Learning Workflows: A Conceptual Framework for the State-of-the-Practice](https://mlsanity.com/paper/2203.08638/) (2022)
- [DMOps: Data Management Operation and Recipes](https://mlsanity.com/paper/2301.01228/) (2023)
- [A Comprehensive Review of AI Agents: Transforming Possibilities in Technology and Beyond](https://mlsanity.com/paper/2508.11957/) (2025)

## Abstract (arXiv)

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.