Search papers, labs, and topics across Lattice.
This paper introduces FinanceHarness, an autonomous framework designed specifically for financial deep research, addressing the inadequacies of general-purpose deep research systems. By integrating finance-oriented tools and workflows, it automates the entire research process while ensuring that future information leakage is prevented through a structured benchmarking approach. The framework's effectiveness is evidenced by a significant improvement in rubric scores, from 25.3% to 32.4%, despite leading LLMs and agents scoring below 40% on the same metrics, highlighting the framework's challenging nature and the need for specialized financial expertise.
FinanceHarness not only automates financial deep research but also reveals that even advanced LLMs struggle with specialized financial tasks, scoring below 40% on rigorous benchmarks.
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.
