Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2511.14299 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914168125259776 |
|---|---|
| author | Liu, Xiaochuan Song, Yuanfeng Yin, Xiaoming Chen, Xing |
| author_facet | Liu, Xiaochuan Song, Yuanfeng Yin, Xiaoming Chen, Xing |
| contents | In today's data-driven era, fully automated end-to-end data analytics, particularly insight discovery, is critical for discovering actionable insights that assist organizations in making effective decisions. With the rapid advancement of large language models (LLMs), LLM-driven agents have emerged as a promising paradigm for automating data analysis and insight discovery. However, existing data insight agents remain limited in several key aspects, often failing to deliver satisfactory results due to: (1) insufficient utilization of domain knowledge, (2) shallow analytical depth, and (3) error-prone code generation during insight generation. To address these issues, we propose DataSage, a novel multi-agent framework that incorporates three innovative features including external knowledge retrieval to enrich the analytical context, a multi-role debating mechanism to simulate diverse analytical perspectives and deepen analytical depth, and multi-path reasoning to improve the accuracy of the generated code and insights. Extensive experiments on InsightBench demonstrate that DataSage consistently outperforms existing data insight agents across all difficulty levels, offering an effective solution for automated data insight discovery. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2511_14299 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DataSage: Multi-agent Collaboration for Insight Discovery with External Knowledge Retrieval, Multi-role Debating, and Multi-path Reasoning Liu, Xiaochuan Song, Yuanfeng Yin, Xiaoming Chen, Xing Artificial Intelligence Computation and Language Multiagent Systems In today's data-driven era, fully automated end-to-end data analytics, particularly insight discovery, is critical for discovering actionable insights that assist organizations in making effective decisions. With the rapid advancement of large language models (LLMs), LLM-driven agents have emerged as a promising paradigm for automating data analysis and insight discovery. However, existing data insight agents remain limited in several key aspects, often failing to deliver satisfactory results due to: (1) insufficient utilization of domain knowledge, (2) shallow analytical depth, and (3) error-prone code generation during insight generation. To address these issues, we propose DataSage, a novel multi-agent framework that incorporates three innovative features including external knowledge retrieval to enrich the analytical context, a multi-role debating mechanism to simulate diverse analytical perspectives and deepen analytical depth, and multi-path reasoning to improve the accuracy of the generated code and insights. Extensive experiments on InsightBench demonstrate that DataSage consistently outperforms existing data insight agents across all difficulty levels, offering an effective solution for automated data insight discovery. |
| title | DataSage: Multi-agent Collaboration for Insight Discovery with External Knowledge Retrieval, Multi-role Debating, and Multi-path Reasoning |
| topic | Artificial Intelligence Computation and Language Multiagent Systems |
| url | https://arxiv.org/abs/2511.14299 |