paper-with-me

홈 › Papers

DataSage: Multi-agent Collaboration for Insight Discovery with External Knowledge Retrieval, Multi-role Debating, and Multi-path Reasoning

2025-11-18 · Xiaochuan Liu, Yuanfeng Song, Xiaoming Yin, Xing Chen arxiv

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.

📄 PDF Abstract BibTeX arXiv:2511.14299

Code (0)

등록된 구현이 없습니다.

Tasks

Code Generation

Similar Papers 제목 키워드 기반

Explanova: Automatically Discover Data Insights in N \times M Table via XAI Combined LLM Workflow

2026-01-18 · Yiming Huang arxiv

Automation in data analysis has been a long-time pursuit. Current agentic LLM shows a promising solution towards it. Like DeepAnalyze, DataSage, and Datawise. They are all powerful agentic frameworks for automatic fine-g…

Federation over Text: Insight Sharing for Multi-Agent Reasoning

2026-04-18 · Dixi Yao, Tahseen Rabbani, Manzil Zaheer, Tian Li arxiv

We propose a federated learning-like framework, Federation over Text (FoT), that enables multiple clients solving different tasks to collectively generate a shared library of metacognitive insights by iteratively federat…

Federated Learning

Cyber Academia-Chemical Engineering (CA-ChemE): A Living Digital Town for Self-Directed Research Evolution and Emergent Scientific Discovery

2025-10-01 · Zekun Jiang, Chunming Xu, Tianhang Zhou arxiv

The rapid advancement of artificial intelligence (AI) has demonstrated substantial potential in chemical engineering, yet existing AI systems remain limited in interdisciplinary collaboration and exploration of uncharted…

MAGIC-MASK: Multi-Agent Guided Inter-Agent Collaboration with Mask-Based Explainability for Reinforcement Learning

2025-09-30 · Maisha Maliha, Dean Hougen arxiv

Understanding the decision-making process of Deep Reinforcement Learning agents remains a key challenge for deploying these systems in safety-critical and multi-agent environments. While prior explainability methods like…

Multi-agent Reinforcement Learning

EvoSci: A Bio-Inspired Multi-Agent Framework for the Evolution of Scientific Discovery

2026-05-20 · Xiaoyu Xiong, Yuqi Ren, Deyi Xiong arxiv

Large language models (LLMs), have shown strong potential in scientific discovery, yet existing methods still face substantial challenges in the design of research workflows and multi-role collaboration mechanisms. To mi…