DiaTool-DPO: Multi-Turn Direct Preference Optimization for Tool-Augmented Large Language Models

• URL: http://arxiv.org/abs/2504.02882v1
• Date: Wed, 02 Apr 2025 05:47:28 GMT
• Title: DiaTool-DPO: Multi-Turn Direct Preference Optimization for Tool-Augmented Large Language Models
• Authors: Sunghee Jung, Donghun Lee, Shinbok Lee, Gaeun Seo, Daniel Lee, Byeongil Ko, Junrae Cho, Kihyun Kim, Eunggyun Kim, Myeongcheol Shin,
• Abstract summary: We propose DiaTool-DPO, a novel method that enhances TA-LLM's dialogue capabilities through Direct Preference Optimization.<n>We model TA-LLM interactions as a Markov Decision Process with 5 distinct dialogue states and categorize user queries into 3 types based on their state transition trajectories.<n>Our evaluation demonstrates that DiaTool-DPO approaches GPT-4o's performance (94.8% in information gathering, 91% in tool call rejection) with substantial improvements over baseline.
• Score: 7.404161214474878
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Tool-Augmented Larage Language Models (TA-LLMs) have shown promise in real-world applications, but face challenges in handling incomplete queries and out-of-scope requests. While existing approaches rely mainly on Supervised Fine-Tuning with expert trajectories, we propose DiaTool-DPO, a novel method that enhances TA-LLM's dialogue capabilities through Direct Preference Optimization. We model TA-LLM interactions as a Markov Decision Process with 5 distinct dialogue states and categorize user queries into 3 types based on their state transition trajectories. We automatically construct paired trajectory datasets of correct and incorrect dialogue flows and introduce a specialized objective loss for dialogue control. Our comprehensive evaluation demonstrates that DiaTool-DPO approaches GPT-4o's performance (94.8% in information gathering, 91% in tool call rejection) with substantial improvements over baseline (44% and 9.6% respectively) while maintaining core functionality. Our approach opens new possibilities for developing TA-LLMs that can handle diverse real-world scenarios without requiring additional expert demonstrations or human labeling.

Related papers

• One Model to Critique Them All: Rewarding Agentic Tool-Use via Efficient Reasoning [54.580646706013965]
  Reward models (RMs) play a critical role in aligning large language models with human preferences.<n>We introduce ToolRM, a family of lightweight generative RMs tailored for general tool-use scenarios.<n>To build these models, we propose a novel pipeline that constructs pairwise preference data using rule-based scoring and multidimensional sampling.
  arXiv  Detail & Related papers  (2025-10-30T06:08:27Z)
• How Can Input Reformulation Improve Tool Usage Accuracy in a Complex Dynamic Environment? A Study on $τ$-bench [58.114899897566964]
  In a multi-turn conversational environment, large language models (LLMs) often struggle with consistent reasoning and adherence to domain-specific policies.<n>We propose the Input-Reformulation Multi-Agent (IRMA) framework, which automatically reformulates user queries augmented with relevant domain rules.<n>IRMA significantly outperforms ReAct, Function Calling, and Self-Reflection by 16.1%, 12.7%, and 19.1%, respectively.
  arXiv  Detail & Related papers  (2025-08-28T15:57:33Z)
• Acting Less is Reasoning More! Teaching Model to Act Efficiently [87.28134636548705]
  Tool-integrated reasoning augments large language models with the ability to invoke external tools to solve tasks.<n>Current approaches typically optimize only for final correctness without considering the efficiency or necessity of external tool use.<n>We propose a framework that encourages models to produce accurate answers with minimal tool calls.<n>Our approach reduces tool calls by up to 68.3% and improves tool productivity by up to 215.4%, while maintaining comparable answer accuracy.
  arXiv  Detail & Related papers  (2025-04-21T05:40:05Z)
• MARS: A Multi-Agent Framework Incorporating Socratic Guidance for Automated Prompt Optimization [30.748085697067154]
  We propose a Multi-Agent framework incorporating Socratic guidance (MARS) MARS comprises seven agents, each with distinct functionalities, which autonomously use the Planner to devise an optimization path. We conduct extensive experiments on various datasets to validate the effectiveness of our method.
  arXiv  Detail & Related papers  (2025-03-21T06:19:55Z)
• PFDial: A Structured Dialogue Instruction Fine-tuning Method Based on UML Flowcharts [47.18738316044761]
  This dataset contains 12,705 high-quality Chinese dialogue instructions derived from 440 flowcharts containing 5,055 process nodes.<n>Based on PlantUML specification, each flowchart is converted into atomic dialogue units i.e., structured five-tuples.<n> Experimental results demonstrate that a 7B model trained with merely 800 samples, and a 0.5B model trained on total data both can surpass 90% accuracy.
  arXiv  Detail & Related papers  (2025-03-09T17:43:30Z)
• AutoLogi: Automated Generation of Logic Puzzles for Evaluating Reasoning Abilities of Large Language Models [86.83875864328984]
  We propose an automated method for synthesizing open-ended logic puzzles, and use it to develop a bilingual benchmark, AutoLogi.<n>Our approach features program-based verification and controllable difficulty levels, enabling more reliable evaluation that better distinguishes models' reasoning abilities.
  arXiv  Detail & Related papers  (2025-02-24T07:02:31Z)
• Evaluating and Enhancing Out-of-Domain Generalization of Task-Oriented Dialog Systems for Task Completion without Turn-level Dialog Annotations [2.453775887722866]
  This work explores whether large language models (LLMs) can be fine-tuned solely on natural language dialogs to perform ToD tasks, without requiring such annotations.<n>We find that models fine-tuned without turn-level annotations generate coherent and contextually appropriate responses.<n>We propose ZeroToD, a framework that incorporates a schema augmentation mechanism to enhance API call accuracy and overall task completion rates.
  arXiv  Detail & Related papers  (2025-02-18T22:10:51Z)
• ChatSOP: An SOP-Guided MCTS Planning Framework for Controllable LLM Dialogue Agents [52.7201882529976]
  We propose SOP-guided Monte Carlo Tree Search (MCTS) planning framework to enhance controllability of dialogue agents.<n>To enable this, we curate a dataset comprising SOP-annotated multi-scenario dialogues, generated using a semi-automated role-playing system with GPT-4o.<n>We also propose a novel method that integrates Chain of Thought reasoning with supervised fine-tuning for SOP prediction.
  arXiv  Detail & Related papers  (2024-07-04T12:23:02Z)
• Self-Augmented Preference Optimization: Off-Policy Paradigms for Language Model Alignment [104.18002641195442]
  We introduce Self-Augmented Preference Optimization (SAPO), an effective and scalable training paradigm that does not require existing paired data. Building on the self-play concept, which autonomously generates negative responses, we further incorporate an off-policy learning pipeline to enhance data exploration and exploitation.
  arXiv  Detail & Related papers  (2024-05-31T14:21:04Z)
• Large Language Models as Zero-shot Dialogue State Tracker through Function Calling [42.00097476584174]
  We propose a novel approach for solving dialogue state tracking with large language models (LLMs) through function calling. This method improves zero-shot DST, allowing adaptation to diverse domains without extensive data collection or model tuning. We show that our approach achieves exceptional performance with both modestly sized open-source and also proprietary LLMs.
  arXiv  Detail & Related papers  (2024-02-16T06:13:18Z)
• Application of frozen large-scale models to multimodal task-oriented dialogue [0.0]
  We use the existing Large Language Models ENnhanced to See Framework (LENS Framework) to test the feasibility of multimodal task-oriented dialogues. The LENS Framework has been proposed as a method to solve computer vision tasks without additional training and with fixed parameters of pre-trained models.
  arXiv  Detail & Related papers  (2023-10-02T01:42:28Z)
• Unlocking the Potential of User Feedback: Leveraging Large Language Model as User Simulator to Enhance Dialogue System [65.93577256431125]
  We propose an alternative approach called User-Guided Response Optimization (UGRO) to combine it with a smaller task-oriented dialogue model. This approach uses LLM as annotation-free user simulator to assess dialogue responses, combining them with smaller fine-tuned end-to-end TOD models. Our approach outperforms previous state-of-the-art (SOTA) results.
  arXiv  Detail & Related papers  (2023-06-16T13:04:56Z)
• RADDLE: An Evaluation Benchmark and Analysis Platform for Robust Task-oriented Dialog Systems [75.87418236410296]
  We introduce the RADDLE benchmark, a collection of corpora and tools for evaluating the performance of models across a diverse set of domains. RADDLE is designed to favor and encourage models with a strong generalization ability. We evaluate recent state-of-the-art systems based on pre-training and fine-tuning, and find that grounded pre-training on heterogeneous dialog corpora performs better than training a separate model per domain.
  arXiv  Detail & Related papers  (2020-12-29T08:58:49Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.