InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents

• URL: http://arxiv.org/abs/2511.22884v1
• Date: Fri, 28 Nov 2025 05:19:24 GMT
• Title: InsightEval: An Expert-Curated Benchmark for Assessing Insight Discovery in LLM-Driven Data Agents
• Authors: Zhenghao Zhu, Yuanfeng Song, Xin Chen, Chengzhong Liu, Yakun Cui, Caleb Chen Cao, Sirui Han, Yike Guo,
• Abstract summary: We develop a data-curation pipeline to construct a new dataset named InsightEval.<n>We highlight prevailing challenges in automated insight discovery and raise some key findings to guide future research.
• Score: 31.43134407708759
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Data analysis has become an indispensable part of scientific research. To discover the latent knowledge and insights hidden within massive datasets, we need to perform deep exploratory analysis to realize their full value. With the advent of large language models (LLMs) and multi-agent systems, more and more researchers are making use of these technologies for insight discovery. However, there are few benchmarks for evaluating insight discovery capabilities. As one of the most comprehensive existing frameworks, InsightBench also suffers from many critical flaws: format inconsistencies, poorly conceived objectives, and redundant insights. These issues may significantly affect the quality of data and the evaluation of agents. To address these issues, we thoroughly investigate shortcomings in InsightBench and propose essential criteria for a high-quality insight benchmark. Regarding this, we develop a data-curation pipeline to construct a new dataset named InsightEval. We further introduce a novel metric to measure the exploratory performance of agents. Through extensive experiments on InsightEval, we highlight prevailing challenges in automated insight discovery and raise some key findings to guide future research in this promising direction.

Related papers

• BeyondSWE: Can Current Code Agent Survive Beyond Single-Repo Bug Fixing? [61.247730037229815]
  We introduce BeyondSWE, a comprehensive benchmark that broadens existing evaluations along two axes - resolution scope and knowledge scope.<n>To investigate the role of external knowledge, we develop SearchSWE, a framework that integrates deep search with coding abilities.<n>This work offers both a realistic, challenging evaluation benchmark and a flexible framework to advance research toward more capable code agents.
  arXiv  Detail & Related papers  (2026-03-03T17:52:01Z)
• Hunt Instead of Wait: Evaluating Deep Data Research on Large Language Models [19.85460397012729]
  Agency expected of Agentic Large Language Models goes beyond answering correctly, requiring autonomy to set goals and decide what to explore.<n>We term this investigatory intelligence, distinguishing it from executional intelligence, which merely completes assigned tasks.<n>To address this, we introduce Deep Data Research ( DDR), an open-ended task where LLMs autonomously extract key insights from databases, and DDR-Bench, a large-scale, checklist-based benchmark that enables verifiable evaluation.
  arXiv  Detail & Related papers  (2026-02-02T12:36:57Z)
• DataSage: Multi-agent Collaboration for Insight Discovery with External Knowledge Retrieval, Multi-role Debating, and Multi-path Reasoning [10.04895420035484]
  DataSage is a novel multi-agent framework that incorporates external knowledge retrieval to enrich the analytical context.<n>Extensive experiments on InsightBench demonstrate that DataSage consistently outperforms existing data insight agents across all difficulty levels.
  arXiv  Detail & Related papers  (2025-11-18T09:54:13Z)
• InfoDeepSeek: Benchmarking Agentic Information Seeking for Retrieval-Augmented Generation [63.55258191625131]
  InfoDeepSeek is a new benchmark for assessing agentic information seeking in real-world, dynamic web environments.<n>We propose a systematic methodology for constructing challenging queries satisfying the criteria of determinacy, difficulty, and diversity.<n>We develop the first evaluation framework tailored to dynamic agentic information seeking, including fine-grained metrics about the accuracy, utility, and compactness of information seeking outcomes.
  arXiv  Detail & Related papers  (2025-05-21T14:44:40Z)
• Network Intrusion Datasets: A Survey, Limitations, and Recommendations [0.0]
  Data-driven cyberthreat detection has become a crucial defense technique in modern cybersecurity.<n>Despite the importance of data, its scarcity has long been recognized as a major obstacle in NIDS research.
  arXiv  Detail & Related papers  (2025-02-10T17:14:37Z)
• Oriented Tiny Object Detection: A Dataset, Benchmark, and Dynamic Unbiased Learning [51.170479006249195]
  We introduce a new dataset, benchmark, and a dynamic coarse-to-fine learning scheme in this study.<n>Our proposed dataset, AI-TOD-R, features the smallest object sizes among all oriented object detection datasets.<n>We present a benchmark spanning a broad range of detection paradigms, including both fully-supervised and label-efficient approaches.
  arXiv  Detail & Related papers  (2024-12-16T09:14:32Z)
• Trustworthiness in Retrieval-Augmented Generation Systems: A Survey [59.26328612791924]
  Retrieval-Augmented Generation (RAG) has quickly grown into a pivotal paradigm in the development of Large Language Models (LLMs) We propose a unified framework that assesses the trustworthiness of RAG systems across six key dimensions: factuality, robustness, fairness, transparency, accountability, and privacy.
  arXiv  Detail & Related papers  (2024-09-16T09:06:44Z)
• DiscoveryBench: Towards Data-Driven Discovery with Large Language Models [50.36636396660163]
  We present DiscoveryBench, the first comprehensive benchmark that formalizes the multi-step process of data-driven discovery. Our benchmark contains 264 tasks collected across 6 diverse domains, such as sociology and engineering. Our benchmark, thus, illustrates the challenges in autonomous data-driven discovery and serves as a valuable resource for the community to make progress.
  arXiv  Detail & Related papers  (2024-07-01T18:58:22Z)
• Video Anomaly Detection in 10 Years: A Survey and Outlook [10.143205531474907]
  Video anomaly detection (VAD) holds immense importance across diverse domains such as surveillance, healthcare, and environmental monitoring. This survey explores deep learning-based VAD, expanding beyond traditional supervised training paradigms to encompass emerging weakly supervised, self-supervised, and unsupervised approaches.
  arXiv  Detail & Related papers  (2024-05-29T17:56:31Z)
• Object Detectors in the Open Environment: Challenges, Solutions, and Outlook [95.3317059617271]
  The dynamic and intricate nature of the open environment poses novel and formidable challenges to object detectors. This paper aims to conduct a comprehensive review and analysis of object detectors in open environments. We propose a framework that includes four quadrants (i.e., out-of-domain, out-of-category, robust learning, and incremental learning) based on the dimensions of the data / target changes.
  arXiv  Detail & Related papers  (2024-03-24T19:32:39Z)
• Benchmarking Data Science Agents [11.582116078653968]
  Large Language Models (LLMs) have emerged as promising aids as data science agents, assisting humans in data analysis and processing. Yet their practical efficacy remains constrained by the varied demands of real-world applications and complicated analytical process. We introduce DSEval -- a novel evaluation paradigm, as well as a series of innovative benchmarks tailored for assessing the performance of these agents.
  arXiv  Detail & Related papers  (2024-02-27T03:03:06Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.