Saved in:
Bibliographic Details
Main Authors: Zhang, Le, Zhang, Shengming, Zha, Rui, Wu, Yunpeng, Zhou, Jingbo, Huang, Jizhou
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.17900
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913140151681024
author Zhang, Le
Zhang, Shengming
Zha, Rui
Wu, Yunpeng
Zhou, Jingbo
Huang, Jizhou
author_facet Zhang, Le
Zhang, Shengming
Zha, Rui
Wu, Yunpeng
Zhou, Jingbo
Huang, Jizhou
contents Accurate Point of Interest (POI) attribute acquisition is essential for location-based services, yet traditional modular Interactive Voice Response (IVR) systems suffer from error accumulation and high maintenance overhead. We present DuIVRS-2, a large language model (LLM)-based end-to-end framework designed for large-scale POI attribute acquisition at Baidu Maps. To address the long-tail distribution of real-world interactions, our methodology first employs a finite state machine (FSM)-guided data augmentation strategy to synthesize a balanced and diverse training dataset. We then streamline dialogue management via a selective generation scheme combined with a Chain-of-Thought (CoT) mechanism, which ensures output stability and effectively eliminates hallucinations in industrial settings. To facilitate continuous policy refinement with minimal manual effort, we design a cooperative iterative learning framework that leverages a dual-evaluator voting system. Deployed in production for two months, DuIVRS-2 processed 0.4 million calls daily and achieved a 83.9\% Task Success Rate (TSR), outperforming its predecessor by 4 percentage points while maintaining a low reaction time of 130ms. This work provides a production-proven reference for developing robust, cost-effective LLM agents for large-scale industrial dialogue applications.
format Preprint
id arxiv_https___arxiv_org_abs_2605_17900
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition
Zhang, Le
Zhang, Shengming
Zha, Rui
Wu, Yunpeng
Zhou, Jingbo
Huang, Jizhou
Artificial Intelligence
Accurate Point of Interest (POI) attribute acquisition is essential for location-based services, yet traditional modular Interactive Voice Response (IVR) systems suffer from error accumulation and high maintenance overhead. We present DuIVRS-2, a large language model (LLM)-based end-to-end framework designed for large-scale POI attribute acquisition at Baidu Maps. To address the long-tail distribution of real-world interactions, our methodology first employs a finite state machine (FSM)-guided data augmentation strategy to synthesize a balanced and diverse training dataset. We then streamline dialogue management via a selective generation scheme combined with a Chain-of-Thought (CoT) mechanism, which ensures output stability and effectively eliminates hallucinations in industrial settings. To facilitate continuous policy refinement with minimal manual effort, we design a cooperative iterative learning framework that leverages a dual-evaluator voting system. Deployed in production for two months, DuIVRS-2 processed 0.4 million calls daily and achieved a 83.9\% Task Success Rate (TSR), outperforming its predecessor by 4 percentage points while maintaining a low reaction time of 130ms. This work provides a production-proven reference for developing robust, cost-effective LLM agents for large-scale industrial dialogue applications.
title DuIVRS-2: An LLM-based Interactive Voice Response System for Large-scale POI Attribute Acquisition
topic Artificial Intelligence
url https://arxiv.org/abs/2605.17900