TwinBI: An Agentic Digital Twin for Efficient Augmented Interactions with Business Intelligence Dashboards
Quick Answer
This paper shows that TwinBI integrates an LLM-based agent with a BI dashboard, enhancing analytical consistency and user interaction.
Quick Take
It boosts exact-match accuracy from 43.3% to 63.3% and reduces timeout rates from 40% to 10%, demonstrating significant improvements in multi-step analysis workflows.
Key Points
- TwinBI couples -based agents with executable BI dashboard states.
- Exact-match accuracy improved from 43.3% to 63.3% in A/B testing.
- Timeout rates reduced from 40% to 10% compared to traditional dashboards.
- Usability study showed high task accuracy and favorable user ratings.
- Artifacts like SQL and insights command enhance analytical summaries.
Paper Resources
Article Content
From source RSS / original summaryarXiv:2606. 13731v1 Announce Type: new Abstract: Business intelligence (BI) increasingly combines dashboard interaction with -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
Want this in your inbox every morning?
Daily brief at your local 8am — bilingual EN/中文, free.
More from arXiv cs.AI
See more →HOBA: Hierarchical On-Policy Bidding Agents for Adaptive Online Advertising
HOBA (Hierarchical On-policy Bidding Agents) is a novel hierarchical reinforcement learning framework that enhances online advertising bidding systems by improving adaptability and reducing hyperparameter tuning costs. It utilizes a for hyperparameter inference, a SARSA agent for expert model selection, and a dynamic expert pool for bid execution, achieving a +3.6% increase in target cost during large-scale deployment and outperforming state-of-the-art baselines on AuctionNet.