# Empowering LLMs in Task-Oriented Dialogues: A Domain-Independent Multi-Agent Framework and Fine-Tuning Strategy

arXiv: https://arxiv.org/abs/2505.14299 · HTML: https://mlsanity.com/paper/2505.14299/

## Key facts

- Cited by 3 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 21 of its 32 references that are in the map.
- First posted on arXiv 20 May 2025.

## Placed in

- LLM agents and tool use / [General LLM agent frameworks and benchmarks](https://mlsanity.com/agents/general-llm-agent-frameworks-and-benchmarks/)
- LLM alignment / RLHF / preference optimisation / [LLM preference optimization methods](https://mlsanity.com/alignment/llm-preference-optimization-methods/)

## Builds on (most cited first, 21 of 21)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Improving Factuality and Reasoning in Language Models through Multiagent Debate](https://mlsanity.com/paper/2305.14325/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [MedAgents: Large Language Models as Collaborators for Zero-shot Medical Reasoning](https://mlsanity.com/paper/2311.10537/) (2023)
- [Smaug: Fixing Failure Modes of Preference Optimisation with DPO-Positive](https://mlsanity.com/paper/2402.13228/) (2024)
- [MultiWOZ 2.2 : A Dialogue Dataset with Additional Annotation Corrections and State Tracking Baselines](https://mlsanity.com/paper/2007.12720/) (2020)
- [GALAXY: A Generative Pre-trained Model for Task-Oriented Dialog with Semi-Supervised Learning and Explicit Policy Injection](https://mlsanity.com/paper/2111.14592/) (2021)
- [Small LLMs Are Weak Tool Learners: A Multi-LLM Agent](https://mlsanity.com/paper/2401.07324/) (2024)
- [Recent Advances and Challenges in Task-oriented Dialog System](https://mlsanity.com/paper/2003.07490/) (2020)
- [Towards Analyzing and Understanding the Limitations of DPO: A Theoretical Perspective](https://mlsanity.com/paper/2404.04626/) (2024)
- [Making Large Language Models Better Reasoners with Alignment](https://mlsanity.com/paper/2309.02144/) (2023)
- [GODEL: Large-Scale Pre-Training for Goal-Directed Dialog](https://mlsanity.com/paper/2206.11309/) (2022)
- [SGP-TOD: Building Task Bots Effortlessly via Schema-Guided LLM Prompting](https://mlsanity.com/paper/2305.09067/) (2023)
- [Task-Optimized Adapters for an End-to-End Task-Oriented Dialogue System](https://mlsanity.com/paper/2305.02468/) (2023)
- [Improving Generalization in Intent Detection: GRPO with Reward-Based Curriculum Sampling](https://mlsanity.com/paper/2504.13592/) (2025)
- [Mars: Modeling Context & State Representations with Contrastive Learning for End-to-End Task-Oriented Dialog](https://mlsanity.com/paper/2210.08917/) (2022)
- [KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning](https://mlsanity.com/paper/2211.16773/) (2022)
- [DARD: A Multi-Agent Approach for Task-Oriented Dialog Systems](https://mlsanity.com/paper/2411.00427/) (2024)
- [Learning from Relevant Subgoals in Successful Dialogs using Iterative Training for Task-oriented Dialog Systems](https://mlsanity.com/paper/2411.16305/) (2024)

## Built on by (most cited first, 3 of 3)

- [ProST: Progressive Sub-task Training for Pareto-Optimal Multi-agent Systems Using Small Language Models](https://mlsanity.com/paper/2509.04508/) (2025)
- [Teaching LLM to be Persuasive: Reward-Enhanced Policy Optimization for Alignment from Heterogeneous Rewards](https://mlsanity.com/paper/2510.04214/) (2025)
- [Prompt reinforcing for long-term planning of large language models](https://mlsanity.com/paper/2510.05921/) (2025)

## Abstract (arXiv)

Task-oriented dialogue systems based on Large Language Models (LLMs) have gained increasing attention across various industries and achieved significant results. Current approaches condense complex procedural workflows into a single agent to achieve satisfactory performance on large-scale LLMs. However, these approaches face challenges to achieve comparable performance on fine-tuned lightweight LLMs, due to their limited capabilities in handling multiple complex logic. In this work, we design a Domain-Independent Multi-Agent Framework (DIMF), which contains Intent Classification Agent, Slot Filling Agent and Response Agent. This approach simplifies the learning complexity and enhances the generalization ability by separating the tasks into domain-independent components. In this framework, we enhance the capabilities in contextual understanding using the Direct Preference Optimisation (DPO) method, and propose a simple and effective Data Distribution Adaptation (DDA) method to mitigate degradation issues during DPO training. Experiments conducted on the MultiWOZ datasets show that our proposed method achieves a better average performance among all the baselines. Extensive analysis also demonstrates that our proposed framework exhibits excellent generalizability and zero-shot capability.