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

• URL: http://arxiv.org/abs/2603.24051v1
• Date: Wed, 25 Mar 2026 08:00:26 GMT
• Title: FinToolSyn: A forward synthesis Framework for Financial Tool-Use Dialogue Data with Dynamic Tool Retrieval
• Abstract summary: FinToolSyn is a forward synthesis framework designed to generate high-quality financial dialogues.<n>Our pipeline constructs a repository of 43,066 tools and synthesizes over 148k dialogue instances.<n>Extensive experiments demonstrate that models trained on FinToolSyn achieve a 21.06% improvement.
• Score: 59.67674731525128
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: 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.

Related papers

• VESTA: Visual Exploration with Statistical Tool Agents [56.76643750765825]
  We introduce VESTA: Visual Exploration with Statistical Tool Agents.<n>We show that VESTA's dynamic tool creation outperforms prior agentic pipelines.<n>We also introduce DAWN, a benchmark targeting distribution fitting and time series.
  arXiv  Detail & Related papers  (2026-05-29T21:57:37Z)
• ToolWeave: Structured Synthesis of Complex Multi-Turn Tool-Calling Dialogues [17.032111974825185]
  Multi-turn tool calling is essential for LLMs to function as autonomous agents.<n>Existing synthetic data generation pipelines produce unrealistic dialogues.<n>We introduce ToolWeave, a structured framework for synthesizing realistic multi-turn tool-calling.
  arXiv  Detail & Related papers  (2026-04-03T17:02:20Z)
• Unlocking Implicit Experience: Synthesizing Tool-Use Trajectories from Text [48.25052564552558]
  We introduce GEM, a data synthesis pipeline that enables the generation and extraction of multi-turn tool-use trajectories from text corpora.<n>To reduce the computational cost, we further train a specialized Trajectory Synthesizer via supervised fine-tuning.<n>Experiments demonstrate that our GEM-32B achieve a 16.5% improvement on the BFCL V3 Multi-turn benchmark.
  arXiv  Detail & Related papers  (2026-01-15T12:58:46Z)
• Simulating Complex Multi-Turn Tool Calling Interactions in Stateless Execution Environments [14.539418822648658]
  DiGiT-TC is designed to produce tool calling conversations that have the characteristics of conversations generated through search in a stateful environment.<n>We validate our approach on standard tool calling benchmarks and demonstrate that, even in stateful problem settings, our approach results in strong performance gains.
  arXiv  Detail & Related papers  (2026-01-06T20:04:30Z)
• SynthTools: A Framework for Scaling Synthetic Tools for Agent Development [5.411691071249542]
  We introduce SynthTools, a flexible and scalable framework for generating synthetic tool ecosystems.<n>Our framework consists of three core components: Tool Generation for automatic and scalable creation of diverse tools, Tool Simulation to emulate realistic tool behaviors, and Tool Audit to ensure correctness and consistency of tool simulation.<n>By enabling scalable, diverse, and reliable tool ecosystems, SynthTools provides a practical path toward large-scale training and stable evaluation of tool-use agents.
  arXiv  Detail & Related papers  (2025-11-11T19:26:40Z)
• FinSight: Towards Real-World Financial Deep Research [68.31086471310773]
  FinSight is a novel framework for producing high-quality, multimodal financial reports.<n>To ensure professional-grade visualization, we propose an Iterative Vision-Enhanced Mechanism.<n>A two-stage Writing Framework expands concise Chain-of-Analysis segments into coherent, citation-aware, and multimodal reports.
  arXiv  Detail & Related papers  (2025-10-19T14:05:35Z)
• ToolFlow: Boosting LLM Tool-Calling Through Natural and Coherent Dialogue Synthesis [80.34000499166648]
  We propose a Graph-based Sampling strategy to sample more relevant tool combinations, and a Planned-generation strategy to create plans that guide the synthesis of coherent dialogues.<n>We apply SFT on LLaMA-3.1-8B using 8,000 synthetic dialogues generated with ToolFlow.<n>Results show that the model achieves tool-calling performance comparable to or even surpassing GPT-4, while maintaining strong general capabilities.
  arXiv  Detail & Related papers  (2024-10-24T05:45:04Z)
• Towards Completeness-Oriented Tool Retrieval for Large Language Models [60.733557487886635]
  Real-world systems often incorporate a wide array of tools, making it impractical to input all tools into Large Language Models. Existing tool retrieval methods primarily focus on semantic matching between user queries and tool descriptions. We propose a novel modelagnostic COllaborative Learning-based Tool Retrieval approach, COLT, which captures not only the semantic similarities between user queries and tool descriptions but also takes into account the collaborative information of tools.
  arXiv  Detail & Related papers  (2024-05-25T06:41:23Z)

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.