CoeusBI: A Comprehensive Interactive Business Intelligence System Powered by LLMs at Baidu

CoeusBI: комплексная интерактивная система бизнес-аналитики на основе больших языковых моделей в Baidu
Jinqing Lian, Chaofan Li, Yingxia Shao, Ming Wang, Yang Dong, Xinyi Liu, Wei Zhang, Chaoxian Gui, Tianqi Wan, Ming Dong
2026-08-01

Dual-Agent ArchitectureHierarchical Schema LinkingInteractive Business IntelligenceLarge Language ModelsNatural Language to SQL
The advent of Large Language Models has catalyzed the emergence of interactive Business Intelligence (BI) systems. Although commercial BI products increasingly adopt semantic layers paired with natural language interfaces, they predominantly rely on manual configurations to define metrics and dimensions. Real-world deployments continue to face critical challenges: (a) frequent JOIN operations degrade the accuracy of SQL generation; (b) wide schemas exacerbate the challenge of schema linking; and (c) the generation of dialect-specific queries and the accurate support for multi-round dialogues incur high costs and yield limited accuracy. We introduce CoeusBI, an industrial-scale interactive BI system that addresses these barriers through a novel Dual-Agent Architecture paired with a Hierarchical Schema Linking module: (1) an offline View Generation Agent that utilizes error-feedback to autonomously convert complex JOIN queries into simple single-view queries, which eliminates the need for manual semantic modeling; (2) a Hierarchical Schema Linking module that leverages vector retrieval over views to handle exceptionally wide schemas efficiently; and (3) a dynamic Routing Agent that evaluates dialogue contexts to route queries, dynamically invoking either the synthesis of new intermediate representations or targeted modifications of existing ones, before compiling the unified representation via a deterministic SQL compiler that is agnostic to dialects. Extensive experiments on both public datasets and production datasets demonstrate that CoeusBI achieves significant improvements in query accuracy, token efficiency, and user satisfaction relative to existing methods. CoeusBI is currently deployed as a standalone service on the data platform of Baidu and is widely used across multiple business lines—including video, search, and advertising—supporting thousands of users daily. This work was done while ★ Jinqing Lian and ★ Tianqi Wan worked at Baidu.
1
A dynamic Routing Agent handles multi-round dialogues by selecting between new intermediate-representation synthesis and targeted modification of existing representations.
2
An offline View Generation Agent uses error feedback to transform complex JOIN queries into simple single-view queries, eliminating manual semantic modeling.
3
CoeusBI introduces a dual-agent architecture with hierarchical schema linking for industrial-scale interactive business intelligence.
4
Experiments on public and production datasets show significant gains in query accuracy, token efficiency, and user satisfaction; Baidu deploys CoeusBI across multiple business lines for thousands of daily users.
5
Hierarchical vector retrieval over generated views improves schema linking efficiency for exceptionally wide database schemas.

CoeusBI industrial-scale interactive Business Intelligence system for natural-language querying of wide-schema data sources

query-generation accuracy, schema-linking efficiency, dialect-independent SQL compilation, and multi-round dialogue support

Publication Details
Publication Date
2026-08-01
Journal
Publisher
ISSN
Access Type
Author Information
Authors
Jinqing Lian
Chaofan Li
Yingxia Shao
Ming Wang
Yang Dong
Xinyi Liu
Wei Zhang
Chaoxian Gui
Tianqi Wan
Ming Dong
Explore further
Open the scid.ai AI chat with a ready-made request: it will find papers on a similar topic and help build a literature review.
Find similar papers in the chat →
Make a presentation
100%