# Enhancing Dialogue State Tracking Models through LLM-backed User-Agents Simulation

arXiv: https://arxiv.org/abs/2405.13037 · HTML: https://mlsanity.com/paper/2405.13037/

## Key facts

- Cited by 24 papers in the map (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 38 of its 55 references that are in the map.
- First posted on arXiv 17 May 2024.

## 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, 30 of 38)

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [SGDR: Stochastic Gradient Descent with Warm Restarts](https://mlsanity.com/paper/1608.03983/) (2016)
- [Character-level Convolutional Networks for Text Classification](https://mlsanity.com/paper/1509.01626/) (2015)
- [SpecAugment: A Simple Data Augmentation Method for Automatic Speech Recognition](https://mlsanity.com/paper/1904.08779/) (2019)
- [EDA: Easy Data Augmentation Techniques for Boosting Performance on Text Classification Tasks](https://mlsanity.com/paper/1901.11196/) (2019)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Unified Language Model Pre-training for Natural Language Understanding and Generation](https://mlsanity.com/paper/1905.03197/) (2019)
- [PyTorch FSDP: Experiences on Scaling Fully Sharded Data Parallel](https://mlsanity.com/paper/2304.11277/) (2023)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [Transferable Multi-Domain State Generator for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/1905.08743/) (2019)
- [MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines](https://mlsanity.com/paper/2007.12720/) (2020)
- [Neural Belief Tracker: Data-Driven Dialogue State Tracking](https://mlsanity.com/paper/1606.03777/) (2016)
- [TripPy: A Triple Copy Strategy for Value Independent Neural Dialog State Tracking](https://mlsanity.com/paper/2005.02877/) (2020)
- [MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2009.12005/) (2020)
- [Dialogue State Tracking with a Language Model using Schema-Driven Prompting](https://mlsanity.com/paper/2109.07506/) (2021)
- [MultiWOZ 2.4: A Multi-Domain Task-Oriented Dialogue Dataset with Essential Annotation Corrections to Improve State Tracking Evaluation](https://mlsanity.com/paper/2104.00773/) (2021)
- [Find or Classify? Dual Strategy for Slot-Value Predictions on Multi-Domain Dialog State Tracking](https://mlsanity.com/paper/1910.03544/) (2019)
- [Dialog State Tracking: A Neural Reading Comprehension Approach](https://mlsanity.com/paper/1908.01946/) (2019)
- [Are LLMs All You Need for Task-Oriented Dialogue?](https://mlsanity.com/paper/2304.06556/) (2023)
- [MultiWOZ 2.3: A multi-domain task-oriented dialogue dataset enhanced with annotation corrections and co-reference annotation](https://mlsanity.com/paper/2010.05594/) (2020)
- [Description-Driven Task-Oriented Dialog Modeling](https://mlsanity.com/paper/2201.08904/) (2022)
- [Continual Prompt Tuning for Dialog State Tracking](https://mlsanity.com/paper/2203.06654/) (2022)
- [Controllable Dialogue Simulation with In-Context Learning](https://mlsanity.com/paper/2210.04185/) (2022)
- [From Machine Reading Comprehension to Dialogue State Tracking: Bridging the Gap](https://mlsanity.com/paper/2004.05827/) (2020)
- [SPACE-3: Unified Dialog Model Pre-training for Task-Oriented Dialog Understanding and Generation](https://mlsanity.com/paper/2209.06664/) (2022)
- [Bootstrapping LLM-based Task-Oriented Dialogue Agents via Self-Talk](https://mlsanity.com/paper/2401.05033/) (2024)
- [Towards Universal Dialogue State Tracking](https://mlsanity.com/paper/1810.09587/) (2018)
- [Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System](https://mlsanity.com/paper/2305.02468/) (2023)

## Built on by (most cited first, 24 of 24)

- [Goal Alignment in LLM-Based User Simulators for Conversational AI](https://mlsanity.com/paper/2507.20152/) (2025)
- [The Imperative of Conversation Analysis in the Era of LLMs: A Survey of Tasks, Techniques, and Trends](https://mlsanity.com/paper/2409.14195/) (2024)
- [DARD: A Multi-Agent Approach for Task-Oriented Dialog Systems](https://mlsanity.com/paper/2411.00427/) (2024)
- [A Desideratum for Conversational Agents: Capabilities, Challenges, and Future Directions](https://mlsanity.com/paper/2504.16939/) (2025)
- [ProactiveEval: A Unified Evaluation Framework for Proactive Dialogue Agents](https://mlsanity.com/paper/2508.20973/) (2025)
- [AGENT-CQ: Automatic Generation and Evaluation of Clarifying Questions for Conversational Search with LLMs](https://mlsanity.com/paper/2410.19692/) (2024)
- [OnGoal: Tracking and Visualizing Conversational Goals in Multi-Turn Dialogue with Large Language Models](https://mlsanity.com/paper/2508.21061/) (2025)
- [Structured Dialogue System for Mental Health: An LLM Chatbot Leveraging the PM+ Guidelines](https://mlsanity.com/paper/2411.10681/) (2024)
- [DEMO: Reframing Dialogue Interaction with Fine-grained Element Modeling](https://mlsanity.com/paper/2412.04905/) (2024)
- [Can Large Language Models Keep Up? Benchmarking Online Adaptation to Continual Knowledge Streams](https://mlsanity.com/paper/2603.07392/) (2026)
- [Interpretable and Robust Dialogue State Tracking via Natural Language Summarization with LLMs](https://mlsanity.com/paper/2503.08857/) (2025)
- [TurnWise: The Gap between Single- and Multi-turn Language Model Capabilities](https://mlsanity.com/paper/2603.16759/) (2026)
- [Prior Lessons of Incremental Dialogue and Robot Action Management for the Age of Language Models](https://mlsanity.com/paper/2501.00953/) (2025)
- [AgentTutor: Empowering Personalized Learning with Multi-Turn Interactive Teaching in Intelligent Education Systems](https://mlsanity.com/paper/2601.04219/) (2025)
- [Alopex: A Computational Framework for Enabling On-Device Function Calls with LLMs](https://mlsanity.com/paper/2411.05209/) (2024)
- [A Concise Agent is Less Expert: Revealing Side Effects of Using Style Features on Conversational Agents](https://mlsanity.com/paper/2601.10809/) (2026)
- [Agentic Persona Control and Task State Tracking for Realistic User Simulation in Interactive Scenarios](https://mlsanity.com/paper/2601.15290/) (2025)
- [Distributed Partial Information Puzzles: Examining Common Ground Construction Under Epistemic Asymmetry](https://mlsanity.com/paper/2603.05450/) (2026)
- [Self-supervised Attribute-aware Dynamic Preference Ranking Alignment](https://mlsanity.com/paper/2502.12189/) (2025)
- [SLURG: Investigating the Feasibility of Generating Synthetic Online Fallacious Discourse](https://mlsanity.com/paper/2504.12466/) (2025)
- [From What to Respond to When to Respond: Timely Response Generation for Open-domain Dialogue Agents](https://mlsanity.com/paper/2506.14285/) (2025)
- [HiCoLoRA: Addressing Context-Prompt Misalignment via Hierarchical Collaborative LoRA for Zero-Shot DST](https://mlsanity.com/paper/2509.19742/) (2025)
- [Hybrid Dialogue State Tracking for Persian Chatbots: A Language Model-Based Approach](https://mlsanity.com/paper/2510.01052/) (2025)
- [ESAinsTOD: A Unified End-to-End Schema-Aware Instruction-Tuning Framework for Task-Oriented Dialog Modeling](https://mlsanity.com/paper/2603.09691/) (2026)

## Abstract (arXiv)

Dialogue State Tracking (DST) is designed to monitor the evolving dialogue state in the conversations and plays a pivotal role in developing task-oriented dialogue systems. However, obtaining the annotated data for the DST task is usually a costly endeavor. In this paper, we focus on employing LLMs to generate dialogue data to reduce dialogue collection and annotation costs. Specifically, GPT-4 is used to simulate the user and agent interaction, generating thousands of dialogues annotated with DST labels. Then a two-stage fine-tuning on LLaMA 2 is performed on the generated data and the real data for the DST prediction. Experimental results on two public DST benchmarks show that with the generated dialogue data, our model performs better than the baseline trained solely on real data. In addition, our approach is also capable of adapting to the dynamic demands in real-world scenarios, generating dialogues in new domains swiftly. After replacing dialogue segments in any domain with the corresponding generated ones, the model achieves comparable performance to the model trained on real data.