Full Text:
<9>
CLC number:
On-line Access: 2025-09-19
Received: 2025-06-15
Revision Accepted: 2025-08-25
Crosschecked: 0000-00-00
Cited: 0
Clicked: 22
FinSphere: a real-time stock analysis agent with instruction-tuned LLMs and domain-specific tool integration
| |||||||||||||
Shijie HAN1,3, Jingshu ZHANG1,3, Yiqing SHEN3,4, Kaiyuan YAN3,, Hongguang LI3,. FinSphere: a real-time stock analysis agent with instruction-tuned LLMs and domain-specific tool integration[J]. Frontiers of Information Technology & Electronic Engineering, 1998, -1(-1): .
@article{title="FinSphere: a real-time stock analysis agent with instruction-tuned LLMs and domain-specific tool integration",
author="Shijie HAN1,3, Jingshu ZHANG1,3, Yiqing SHEN3,4, Kaiyuan YAN3,, Hongguang LI3,",
journal="Frontiers of Information Technology & Electronic Engineering",
volume="-1",
number="-1",
pages="",
year="1998",
publisher="Zhejiang University Press & Springer",
doi="10.1631/FITEE.2500414"
}
%0 Journal Article
%T FinSphere: a real-time stock analysis agent with instruction-tuned LLMs and domain-specific tool integration
%A Shijie HAN1
%A 3
%A Jingshu ZHANG1
%A 3
%A Yiqing SHEN3
%A 4
%A Kaiyuan YAN3
%A
%A Hongguang LI3
%A
%J Journal of Zhejiang University SCIENCE C
%V -1
%N -1
%P
%@ 2095-9184
%D 1998
%I Zhejiang University Press & Springer
%DOI 10.1631/FITEE.2500414
TY - JOUR
T1 - FinSphere: a real-time stock analysis agent with instruction-tuned LLMs and domain-specific tool integration
A1 - Shijie HAN1
A1 - 3
A1 - Jingshu ZHANG1
A1 - 3
A1 - Yiqing SHEN3
A1 - 4
A1 - Kaiyuan YAN3
A1 -
A1 - Hongguang LI3
A1 -
J0 - Journal of Zhejiang University Science C
VL - -1
IS - -1
SP -
EP -
%@ 2095-9184
Y1 - 1998
PB - Zhejiang University Press & Springer
ER -
DOI - 10.1631/FITEE.2500414
Abstract: Current financial large language models (FinLLMs) exhibit two major limitations: the absence of standardized evaluation metrics for stock analysis quality and insufficient analytical depth. We address these limitations with two contributions. First, we introduce AnalyScore, a systematic framework for evaluating the quality of stock analysis. Second, we construct Stocksis, an expert-curated dataset designed to enhance LLMs'financial analysis capabilities. Building on Stocksis, together with a novel integration framework and quantitative tools, we develop FinSphere, an AI agent that generates professional-grade stock analysis reports. Evaluations with AnalyScore show that FinSphere consistently surpasses general-purpose LLMs, domain-specific FinLLMs, and existing agent-based systems, even when the latter are enhanced with real-time data access and few-shot guidance. The findings highlight FinSphere's significant advantages in analytical quality and real-world applicability.
Open peer comments: Debate/Discuss/Question/Opinion
<1>