FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Huang, Caishuang, Qiao, Yang, Zhang, Rongyu, Ye, Junjie, Lu, Pu, Wu, Wenxi, Zhou, Meng, Du, Xiku, Gui, Tao, Zhang, Qi, Huang, Xuanjing
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917361086365696
author Huang, Caishuang
Qiao, Yang
Zhang, Rongyu
Ye, Junjie
Lu, Pu
Wu, Wenxi
Zhou, Meng
Du, Xiku
Gui, Tao
Zhang, Qi
Huang, Xuanjing
author_facet Huang, Caishuang
Qiao, Yang
Zhang, Rongyu
Ye, Junjie
Lu, Pu
Wu, Wenxi
Zhou, Meng
Du, Xiku
Gui, Tao
Zhang, Qi
Huang, Xuanjing
contents Tool-use capabilities are vital for Large Language Models (LLMs) in finance, a domain characterized by massive investment targets and data-intensive inquiries. However, existing data synthesis methods typically rely on a reverse synthesis paradigm, generating user queries from pre-sampled tools. This approach inevitably introduces artificial explicitness, yielding queries that fail to capture the implicit, event-driven nature of real-world needs. Moreover, its reliance on static tool sets overlooks the dynamic retrieval process required to navigate massive tool spaces. To address these challenges, we introduce \textit{FinToolSyn}, a forward synthesis framework designed to generate high-quality financial dialogues. Progressing from persona instruction and atomic tool synthesis to dynamic retrieval dialogue generation, our pipeline constructs a repository of 43,066 tools and synthesizes over 148k dialogue instances, incorporating dynamic retrieval to emulate the noisy candidate sets typical of massive tool spaces. We also establish a dedicated benchmark to evaluate tool-calling capabilities in realistic financial scenarios. Extensive experiments demonstrate that models trained on FinToolSyn achieve a 21.06\% improvement, providing a robust foundation for tool learning in financial scenarios.
format Preprint
id arxiv_https___arxiv_org_abs_2603_24051
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval
Huang, Caishuang
Qiao, Yang
Zhang, Rongyu
Ye, Junjie
Lu, Pu
Wu, Wenxi
Zhou, Meng
Du, Xiku
Gui, Tao
Zhang, Qi
Huang, Xuanjing
Computation and Language
Tool-use capabilities are vital for Large Language Models (LLMs) in finance, a domain characterized by massive investment targets and data-intensive inquiries. However, existing data synthesis methods typically rely on a reverse synthesis paradigm, generating user queries from pre-sampled tools. This approach inevitably introduces artificial explicitness, yielding queries that fail to capture the implicit, event-driven nature of real-world needs. Moreover, its reliance on static tool sets overlooks the dynamic retrieval process required to navigate massive tool spaces. To address these challenges, we introduce \textit{FinToolSyn}, a forward synthesis framework designed to generate high-quality financial dialogues. Progressing from persona instruction and atomic tool synthesis to dynamic retrieval dialogue generation, our pipeline constructs a repository of 43,066 tools and synthesizes over 148k dialogue instances, incorporating dynamic retrieval to emulate the noisy candidate sets typical of massive tool spaces. We also establish a dedicated benchmark to evaluate tool-calling capabilities in realistic financial scenarios. Extensive experiments demonstrate that models trained on FinToolSyn achieve a 21.06\% improvement, providing a robust foundation for tool learning in financial scenarios.
title FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval
topic Computation and Language
url https://arxiv.org/abs/2603.24051