paper-with-me

Papers

DataClawBench: An Agent Benchmark for Exploratory Real-World Financial Data Analysis

2026-05-04 · Qiaohong Zhang, Weihao Ye, Jialong Chen, Yi Luo, BoYuan Li, Bowen Deng, Zibin Zheng, Jianhao Lin, Wei-Shi Zheng, Chuan Chen arxiv

Autonomous data analysis agents are increasingly expected to conduct exploratory analysis with limited human guidance about data. However, existing benchmarks typically evaluate such agents in prior-guided settings, providing selected data sources, explicit data schemas, or cleaned data, thereby understating the exploratory burden. To evaluate this realistic exploratory data analysis task, we introduce DataClawBench, a benchmark built from financial think-tank consulting scenarios where agents must independently explore unfamiliar, noisy, cross-domain data and produce verifiable conclusions. DataClawBench provides a unified real-world data environment with approximately 2.06 million records across enterprise, industry, and policy domains, with native data noise preserved. On top of this data environment, it defines 492 multi-step cross-domain tasks, each annotated with intermediate milestones that diagnose exploration and reasoning failures beyond outcome accuracy. A systematic evaluation of eight advanced LLMs under the OpenClaw agent reveals that exploratory data analysis breaks agent reliability: more exploration does not reliably translate into task-relevant progress or correct final answers.

📄 PDF Abstract BibTeX arXiv:2605.02503

Code (0)

등록된 구현이 없습니다.

Similar Papers 제목 키워드 기반

TextQuests: How Good are LLMs at Text-Based Video Games?

2025-07-31 · Long Phan, Mantas Mazeika, Andy Zou, Dan Hendrycks arxiv

Evaluating AI agents within complex, interactive environments that mirror real-world challenges is critical for understanding their practical capabilities. While existing agent benchmarks effectively assess skills like t…

Data Analysis in the Wild: Benchmarking Large Language Models Against Real-World Data Complexities

2026-07-07 · So Hasegawa, Shailaja Keyur Sampat, Lei Liu, Wei-Peng Chen arxiv

Current benchmarks for evaluating Large Language Models (LLMs) in data analysis often fail to reflect real-world settings. They typically focus on fact retrieval from small tables and overlook the challenges of large mul…

Needle in the Web: A Benchmark for Retrieving Targeted Web Pages in the Wild

2025-12-18 · Yumeng Wang, Tianyu Fan, Lingrui Xu, Chao Huang arxiv

Large Language Models (LLMs) have evolved from simple chatbots into sophisticated agents capable of automating complex real-world tasks, where browsing and reasoning over live web content is key to assessing retrieval an…

TestAgent: A Framework for Domain-Adaptive Evaluation of LLMs via Dynamic Benchmark Construction and Exploratory Interaction

2024-10-15 · Wanying Wang, Zeyu Ma, PengFei Liu, Mingang Chen

As large language models (LLMs) are increasingly deployed to various vertical domains, automatically evaluating their performance across different domains remains a critical challenge. Current evaluation methods often re…

Retrieval-augmented Generation

Self-directed Learning of Action Models using Exploratory Planning

2022-03-07 · Dustin Dannenhauer, Matthew Molineaux, Michael W. Floyd, Noah Reifsnyder 외

Complex, real-world domains may not be fully modeled for an agent, especially if the agent has never operated in the domain before. The agent's ability to effectively plan and act in such a domain is influenced by its kn…