Towards Reliable Agentic Progressive Text-to-Visualization with Verification Rules

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Xu, Wenxin, Zhang, Chen Jason, Wei, Xiaoyong, Li, Haoyang, Kim, Hwanhee, Song, Yuanfeng, Wong, Raymond Chi-Wing
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866911728235708416
author Xu, Wenxin
Zhang, Chen Jason
Wei, Xiaoyong
Li, Haoyang
Kim, Hwanhee
Song, Yuanfeng
Wong, Raymond Chi-Wing
author_facet Xu, Wenxin
Zhang, Chen Jason
Wei, Xiaoyong
Li, Haoyang
Kim, Hwanhee
Song, Yuanfeng
Wong, Raymond Chi-Wing
contents Text-to-Visualization (Text-to-Vis) translates natural language queries into visualization query languages, enabling non-expert users to perform data analysis. However, most existing methods follow a one-shot paradigm that requires users to specify all visualization details in a single round, often leading to cognitive overload and incorrect visualizations. In this paper, we propose PMVis, a progressive multi-turn paradigm for text-to-vis, where users' intents are refined through multi-turn interactions. To support research in this paradigm, we construct PMVisBench, the first dataset designed to capture the progressive and iterative nature of real-world user queries. It is built through VQL simplification and NLQ reconstruction, with explicit rule constraints to ensure each intermediate VQL remains valid and meaningful. Building upon PMVis, we further introduce PMVisAgent, an agent-based framework that simulates realistic user-system dialogues. PMVisAgent consists of a User, a System, and a Validation Agent that performs verification and repair via a ReAct-style tool-use loop to mitigate error accumulation across rounds, with explicit interaction and verification rules to ensure reliability of the multi-agent system. Extensive experiments on PMVisBench demonstrate that PMVisAgent significantly outperforms state-of-the-art text-to-vis baselines. It achieves up to 17.57\% and 23.21\% improvements in execution accuracy in single-table and multi-table settings, respectively, while ablation studies confirm the importance of combining progressive interaction with clarification. The code is available at https://github.com/wxxv/PMVis.
format Preprint
id arxiv_https___arxiv_org_abs_2605_29692
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Towards Reliable Agentic Progressive Text-to-Visualization with Verification Rules
Xu, Wenxin
Zhang, Chen Jason
Wei, Xiaoyong
Li, Haoyang
Kim, Hwanhee
Song, Yuanfeng
Wong, Raymond Chi-Wing
Databases
Text-to-Visualization (Text-to-Vis) translates natural language queries into visualization query languages, enabling non-expert users to perform data analysis. However, most existing methods follow a one-shot paradigm that requires users to specify all visualization details in a single round, often leading to cognitive overload and incorrect visualizations. In this paper, we propose PMVis, a progressive multi-turn paradigm for text-to-vis, where users' intents are refined through multi-turn interactions. To support research in this paradigm, we construct PMVisBench, the first dataset designed to capture the progressive and iterative nature of real-world user queries. It is built through VQL simplification and NLQ reconstruction, with explicit rule constraints to ensure each intermediate VQL remains valid and meaningful. Building upon PMVis, we further introduce PMVisAgent, an agent-based framework that simulates realistic user-system dialogues. PMVisAgent consists of a User, a System, and a Validation Agent that performs verification and repair via a ReAct-style tool-use loop to mitigate error accumulation across rounds, with explicit interaction and verification rules to ensure reliability of the multi-agent system. Extensive experiments on PMVisBench demonstrate that PMVisAgent significantly outperforms state-of-the-art text-to-vis baselines. It achieves up to 17.57\% and 23.21\% improvements in execution accuracy in single-table and multi-table settings, respectively, while ablation studies confirm the importance of combining progressive interaction with clarification. The code is available at https://github.com/wxxv/PMVis.
title Towards Reliable Agentic Progressive Text-to-Visualization with Verification Rules
topic Databases
url https://arxiv.org/abs/2605.29692