VisInteract：面向不完美查询的动态交互式文本到可视化
VisInteract: Towards Dynamic Interactive Text-to-Visualization under Imperfect Queries
- The Hong Kong Polytechnic University（香港理工大学）
- ByteDance（字节跳动）
机构由 AI 辅助整理，请以论文原文为准。
AI总结：
针对不完美查询下的文本到可视化问题，提出VisInteract范式与Vis-MCTS算法，通过交互式意图恢复和增强的蒙特卡洛树搜索，显著提升任务成功率。
AI中文摘要：
现实世界中的可视化请求通常存在歧义、不完整或事实错误，然而现有的文本到可视化（Text-to-Vis）系统假设输入是明确指定的，并一次性生成图表。当查询不完美时，系统必须与用户交互以恢复真实意图，但目前没有基准或方法支持这一动态过程。我们引入了VisInteract，一种将文本到可视化重新定义为交互驱动的意图恢复的新范式，以及VisInteract-Bench，据我们所知，这是首个用于动态交互式文本到可视化的基准，具有受控的不完美注入、用于真实多轮反馈的泄漏控制用户代理，以及双视角（代码和图表）的自动评估。在算法方面，我们提出了Vis-MCTS，一种蒙特卡洛树搜索（MCTS）增强方法，对经典MCTS进行了改进，包括渐进式扩展以驯服树搜索中无界的工具参数空间、跨回滚信息共享使澄清和批评惠及整个搜索树，以及维度感知奖励分解，将标量用户反馈沿数据保真度、视觉设计和意图对齐维度进行路由，以解决异构动作间的信用分配问题。在两个LLM骨干网络上的大量实验表明，Vis-MCTS始终优于所有文本到可视化基线，将端到端任务成功率比最强交互式基线提高了13.40%至16.27%，比非交互式基线提高了5倍以上。
英文摘要：
Real-world visualization requests are routinely ambiguous, incomplete, or factually incorrect, yet existing Text-to-Visualization (Text-to-Vis) systems assume well-specified inputs and produce charts in a single pass. When queries are imperfect, a system must \emph{interact} with the user to recover the true intent, but no benchmark or method supports this dynamic process. We introduce \textbf{VisInteract}, a new paradigm that reframes Text-to-Vis as interaction-driven intent recovery, and \textbf{VisInteract-Bench}, to our knowledge, that is the first benchmark for dynamic interactive Text-to-Vis, featuring controlled imperfection injection, a leakage-controlled User Agent for realistic multi-turn feedback, and dual-perspective (code and chart) automated evaluation. On the algorithmic side, we propose \textbf{Vis-MCTS}, a Monte Carlo Tree Search (MCTS) enhanced method, introducing improvements over classical MCTS, that \emph{Progressive Widening} to tame the unbounded tool-argument space in tree search, \emph{cross-rollout information sharing} so clarifications and critiques benefit the entire search tree, and \emph{Dimension-Aware Reward Decomposition} that routes scalar user feedback along data-fidelity, visual-design, and intent-alignment dimensions to resolve credit assignment across heterogeneous actions. Extensive Experiments across two LLM backbones show that Vis-MCTS consistently outperforms all Text-to-Vis baselines, improving end-to-end task success by $13.40\%$--$16.27\%$ over the strongest interactive baseline and by more than $5\times$ over non-interactive ones.
