Business intelligence (BI) increasingly combines dashboard interaction with LLM-based assistance, but these two modes often fall out of sync during multi-step analysis. As users switch between direct dashboard manipulation and natural-language queries, it becomes difficult to preserve a consistent analytical state across filters, hierarchies, metrics, and chart context. We present TwinBI, an agentic digital-twin framework that couples an LLM-based agent system with an executable BI dashboard state. TwinBI unifies conversational interaction, dashboard manipulation, semantic grounding, and provenance tracking through a shared analytical state reconstructed from a unified interaction log. It also exposes artifacts such as schema views, SQL, logs, and an /insights command for state-grounded analytical summaries. We evaluate TwinBI in two complementary ways. In a controlled A/B benchmark with the same backbone agent, TwinBI improves exact-match accuracy from 43.3% to 63.3%, partial-credit accuracy from 48.3% to 70.8%, and substantially reduces timeout rate from 40.0% to 10.0% relative to Dashboard alone. In a usability study, participants benefited from the integrated dashboard-and-chat workflow, with high task accuracy, moderate workload, and favorable ratings for state-aware interaction mechanisms. These results suggest that TwinBI improves both agent-level analytical reliability and user-facing analytical support by turning visible dashboard state into richer actionable context. Our dataset and source code are available at: https://github.com/simonjisu/TwinBI

翻译：商业智能（BI）日益将仪表盘交互与基于大语言模型（LLM）的辅助功能相结合，但在多步骤分析过程中，这两种模式常出现不同步现象。当用户在直接操作仪表盘与自然语言查询之间切换时，跨过滤器、层级、指标和图表上下文保持一致的解析状态变得困难。我们提出TwinBI，一种智能数字孪生框架，将基于LLM的智能体系统与可执行的BI仪表盘状态相耦合。TwinBI通过从统一交互日志重建的共享分析状态，统一了对话交互、仪表盘操作、语义锚定与溯源追踪。它还提供模式视图、SQL、日志等制品，以及用于状态驱动的分析摘要的/insights命令。我们通过两种互补方式评估TwinBI：在相同主干智能体的受控A/B基准测试中，与纯仪表盘模式相比，TwinBI将精确匹配准确率从43.3%提升至63.3%，部分得分准确率从48.3%提升至70.8%，并将超时率从40.0%显著降低至10.0%；在可用性研究中，参与者受益于集成式仪表盘与对话工作流，任务准确率高、工作负荷适中，并对状态感知交互机制给予积极评价。这些结果表明，TwinBI通过将可见仪表盘状态转化为更丰富的可操作上下文，同时提升了智能体层面的分析可靠性以及面向用户的分析支持能力。我们的数据集与源代码开源地址为：https://github.com/simonjisu/TwinBI