{"slug": "twinbi-an-agentic-digital-twin-for-efficient-augmented-interactions-with", "title": "TwinBI: An Agentic Digital Twin for Efficient Augmented Interactions with Business Intelligence Dashboards", "summary": "Researchers introduced TwinBI, an agentic digital-twin framework that synchronizes LLM-based assistance with business intelligence dashboard states, improving exact-match accuracy from 43.3% to 63.3% and reducing timeout rates from 40.0% to 10.0% in benchmarks. The system unifies conversational interaction, dashboard manipulation, and provenance tracking through a shared analytical state, enhancing analytical reliability and user support.", "body_md": "arXiv:2606.13731v1 Announce Type: new\nAbstract: 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", "url": "https://wpnews.pro/news/twinbi-an-agentic-digital-twin-for-efficient-augmented-interactions-with", "canonical_source": "https://arxiv.org/abs/2606.13731", "published_at": "2026-06-15 04:00:00+00:00", "updated_at": "2026-06-15 04:15:04.286219+00:00", "lang": "en", "topics": ["artificial-intelligence", "large-language-models", "ai-agents", "ai-tools", "natural-language-processing"], "entities": ["TwinBI", "arXiv", "GitHub"], "alternates": {"html": "https://wpnews.pro/news/twinbi-an-agentic-digital-twin-for-efficient-augmented-interactions-with", "markdown": "https://wpnews.pro/news/twinbi-an-agentic-digital-twin-for-efficient-augmented-interactions-with.md", "text": "https://wpnews.pro/news/twinbi-an-agentic-digital-twin-for-efficient-augmented-interactions-with.txt", "jsonld": "https://wpnews.pro/news/twinbi-an-agentic-digital-twin-for-efficient-augmented-interactions-with.jsonld"}}