Salvato in:
Dettagli Bibliografici
Autori principali: Guo, Jiacheng, Huang, Suozhi, Yao, Zixin, Zhang, Yifan, Lu, Yifu, Liu, Jiashuo, Li, Zihao, Deng, Nicholas, Xiao, Qixin, Tian, Jia, Zhan, Kanghong, Li, Tianyi, Liu, Xiaochen, Ge, Jason, He, Chaoyang, Huang, Kaixuan, Yang, Lin, Huang, Wenhao, Wang, Mengdi
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2512.00417
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866910222983888896
author Guo, Jiacheng
Huang, Suozhi
Yao, Zixin
Zhang, Yifan
Lu, Yifu
Liu, Jiashuo
Li, Zihao
Deng, Nicholas
Xiao, Qixin
Tian, Jia
Zhan, Kanghong
Li, Tianyi
Liu, Xiaochen
Ge, Jason
He, Chaoyang
Huang, Kaixuan
Yang, Lin
Huang, Wenhao
Wang, Mengdi
author_facet Guo, Jiacheng
Huang, Suozhi
Yao, Zixin
Zhang, Yifan
Lu, Yifu
Liu, Jiashuo
Li, Zihao
Deng, Nicholas
Xiao, Qixin
Tian, Jia
Zhan, Kanghong
Li, Tianyi
Liu, Xiaochen
Ge, Jason
He, Chaoyang
Huang, Kaixuan
Yang, Lin
Huang, Wenhao
Wang, Mengdi
contents This paper introduces CryptoBench, the first expert-curated, dynamic benchmark designed to rigorously evaluate the real-world capabilities of Large Language Model (LLM) agents in the uniquely demanding and fast-paced cryptocurrency domain. Unlike general-purpose agent benchmarks for search and prediction, professional crypto analysis presents specific challenges: \emph{extreme time-sensitivity}, \emph{a highly adversarial information environment}, and the critical need to synthesize data from \emph{diverse, specialized sources}, such as on-chain intelligence platforms and real-time Decentralized Finance (DeFi) dashboards. CryptoBench thus serves as a much more challenging and valuable scenario for LLM agent assessment. To address these challenges, we constructed a live, dynamic benchmark featuring 50 questions per month, expertly designed by crypto-native professionals to mirror actual analyst workflows. These tasks are rigorously categorized within a four-quadrant system: Simple Retrieval, Complex Retrieval, Simple Prediction, and Complex Prediction. This granular categorization enables a precise assessment of an LLM agent's foundational data-gathering capabilities alongside its advanced analytical and forecasting skills. Our evaluation of ten LLMs, both directly and within an agentic framework, reveals a performance hierarchy and uncovers a failure mode. We observe a \textit{retrieval-prediction imbalance}, where many leading models, despite being proficient at data retrieval, demonstrate a pronounced weakness in tasks requiring predictive analysis. This highlights a problematic tendency for agents to appear factually grounded while lacking the deeper analytical capabilities to synthesize information.
format Preprint
id arxiv_https___arxiv_org_abs_2512_00417
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency
Guo, Jiacheng
Huang, Suozhi
Yao, Zixin
Zhang, Yifan
Lu, Yifu
Liu, Jiashuo
Li, Zihao
Deng, Nicholas
Xiao, Qixin
Tian, Jia
Zhan, Kanghong
Li, Tianyi
Liu, Xiaochen
Ge, Jason
He, Chaoyang
Huang, Kaixuan
Yang, Lin
Huang, Wenhao
Wang, Mengdi
Computation and Language
This paper introduces CryptoBench, the first expert-curated, dynamic benchmark designed to rigorously evaluate the real-world capabilities of Large Language Model (LLM) agents in the uniquely demanding and fast-paced cryptocurrency domain. Unlike general-purpose agent benchmarks for search and prediction, professional crypto analysis presents specific challenges: \emph{extreme time-sensitivity}, \emph{a highly adversarial information environment}, and the critical need to synthesize data from \emph{diverse, specialized sources}, such as on-chain intelligence platforms and real-time Decentralized Finance (DeFi) dashboards. CryptoBench thus serves as a much more challenging and valuable scenario for LLM agent assessment. To address these challenges, we constructed a live, dynamic benchmark featuring 50 questions per month, expertly designed by crypto-native professionals to mirror actual analyst workflows. These tasks are rigorously categorized within a four-quadrant system: Simple Retrieval, Complex Retrieval, Simple Prediction, and Complex Prediction. This granular categorization enables a precise assessment of an LLM agent's foundational data-gathering capabilities alongside its advanced analytical and forecasting skills. Our evaluation of ten LLMs, both directly and within an agentic framework, reveals a performance hierarchy and uncovers a failure mode. We observe a \textit{retrieval-prediction imbalance}, where many leading models, despite being proficient at data retrieval, demonstrate a pronounced weakness in tasks requiring predictive analysis. This highlights a problematic tendency for agents to appear factually grounded while lacking the deeper analytical capabilities to synthesize information.
title CryptoBench: A Dynamic Benchmark for Expert-Level Evaluation of LLM Agents in Cryptocurrency
topic Computation and Language
url https://arxiv.org/abs/2512.00417