FinanceHarness: Autonomous Financial Deep Research Framework

• URL: http://arxiv.org/abs/2607.27853v1
• Date: Thu, 30 Jul 2026 08:32:04 GMT
• Title: FinanceHarness: Autonomous Financial Deep Research Framework
• Abstract summary: FinanceHarness runs finance-oriented tools and practitioner-guided, automated financial deep research end to end.<n>FinanceGym comprises thesis-driven research questions and rubrics that combine pre-cutoff and post-cutoff criteria.
• Score: 41.02718376252945
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Powered by advances in LLMs and autonomous agents, deep research has become one of the most widely adopted agentic products. However, most deep research systems write general-purpose reports, which are inadequate for financial deep research. Financial research demands specialized knowledge to analyze historical patterns and forecast upcoming events. Automating financial deep research therefore requires both a layered harness to drive the research agent and a verifiable, point-in-time benchmark that prevents leakage of future information. We present FinanceHarness, a harness that runs finance-oriented tools and practitioner-guided workflows, automating financial deep research end to end: environment and data construction, the agent execution loop, and reward modeling. We further propose FinanceGym, comprising thesis-driven research questions and rubrics that combine pre-cutoff and post-cutoff criteria. Professional expert validation yields an 82% pass rate. Even leading LLMs and agents score below 40% on the rubrics, showing that FinanceGym is challenging and leaves substantial headroom. With the same open-weight backbone, FinanceHarness improves the overall rubric score from 25.3% to 32.4%. FinanceHarness is available at https://github.com/Yijia-Xiao/FinanceHarness.

Related papers

• FinDeepIndicator: Benchmarking Deep Research Agents in End-to-End Financial Indicator Construction [57.909515451254855]
  FinDeepIndicator is the first benchmark dedicated to evaluating Deep Research (DR) agents in end-to-end financial indicator construction.<n>It evaluates DR agents across four stages in indicator construction: formula specification, data collection, indicator calculation, and answer generation.<n>It contains 3,350 curated question-answer pairs derived from both U.S. and Chinese markets, 10 years of historical financial data, and 800 listed companies.
  arXiv  Detail & Related papers  (2026-08-01T16:54:41Z)
• 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)
• FinSearchComp: Towards a Realistic, Expert-Level Evaluation of Financial Search and Reasoning [30.252244345152956]
  FinSearchComp is the first fully open-source benchmark for realistic, open-domain financial search and reasoning.<n>The benchmark includes 635 questions spanning global and Greater China markets.<n>Grok 4 (web) tops the global subset, approaching expert-level accuracy.
  arXiv  Detail & Related papers  (2025-09-16T15:13:13Z)
• FinResearchBench: A Logic Tree based Agent-as-a-Judge Evaluation Framework for Financial Research Agents [15.905856417551737]
  FinResearchBench is a logic tree-based Agent-as-a-Judge and targets specifically for the financial research agents.<n>It provides a comprehensive and automatic assessment of the research agents across 7 key types of tasks in the financial research domain.
  arXiv  Detail & Related papers  (2025-07-22T05:40:25Z)
• FinTeam: A Multi-Agent Collaborative Intelligence System for Comprehensive Financial Scenarios [31.464961691866854]
  FinTeam is a financial multi-agent collaborative system.<n>We train these agents with specific financial expertise using constructed datasets.<n>We evaluate FinTeam on comprehensive financial tasks constructed from real online investment forums.
  arXiv  Detail & Related papers  (2025-07-05T10:12:25Z)
• FinDER: Financial Dataset for Question Answering and Evaluating Retrieval-Augmented Generation [65.04104723843264]
  We present FinDER, an expert-generated dataset tailored for Retrieval-Augmented Generation (RAG) in finance.<n>FinDER focuses on annotating search-relevant evidence by domain experts, offering 5,703 query-evidence-answer triplets.<n>By challenging models to retrieve relevant information from large corpora, FinDER offers a more realistic benchmark for evaluating RAG systems.
  arXiv  Detail & Related papers  (2025-04-22T11:30:13Z)
• FinBen: A Holistic Financial Benchmark for Large Language Models [75.09474986283394]
  FinBen is the first extensive open-source evaluation benchmark, including 36 datasets spanning 24 financial tasks. FinBen offers several key innovations: a broader range of tasks and datasets, the first evaluation of stock trading, novel agent and Retrieval-Augmented Generation (RAG) evaluation, and three novel open-source evaluation datasets for text summarization, question answering, and stock trading.
  arXiv  Detail & Related papers  (2024-02-20T02:16:16Z)
• FinPT: Financial Risk Prediction with Profile Tuning on Pretrained Foundation Models [32.7825479037623]
  FinPT is a novel approach for financial risk prediction that conduct Profile Tuning on large pretrained foundation models. FinBench is a set of high-quality datasets on financial risks such as default, fraud, and churn.
  arXiv  Detail & Related papers  (2023-07-22T09:27:05Z)
• FinQA: A Dataset of Numerical Reasoning over Financial Data [52.7249610894623]
  We focus on answering deep questions over financial data, aiming to automate the analysis of a large corpus of financial documents. We propose a new large-scale dataset, FinQA, with Question-Answering pairs over Financial reports, written by financial experts. The results demonstrate that popular, large, pre-trained models fall far short of expert humans in acquiring finance knowledge.
  arXiv  Detail & Related papers  (2021-09-01T00:08:14Z)

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.