Pıer
TidesCurrentsHarbor LightsLabBottlesAshore
Pıer

Navigation

  • Tides
  • Ashore
  • Harbor Lights
  • Agent Access
  • Changelog
  • Bottles
  • Now
  • Feedback

External links

GitHubCloudborne ↗

© 2026 Pier.

WatchingResearchWatching0 independent reports0

FinanceComplexQA: Benchmarking Agentic Reasoning on Industrial-grade Financial Documents

First seen · 7/24/2026, 12:00 PMLatest activity · 7/24/2026, 12:00 PM

This paper introduces Finance-LaTeX SKILL, an expert-informed method for synthesizing financial documents with complex layouts. Using an agent workflow, the authors generate 2,000 professional documents and 6,000 question-answer pairs. FinanceComplexQA contains 1,009 financial documents and 2,026 open-ended deep-research tasks, with bilingual support, six scenarios, and seven task types. It evaluates leading RAG systems and agentic reasoning tools using Agent-as-a-Judge and multiple metrics, analyzing failures in numerical computation, multi-hop reasoning, summarization, and industry analysis.

Event heat · last 24 hours

No heat snapshots are available in the last 24 hours.

No heat snapshots are available in the last 24 hours.

Reporting Timeline

  1. AggregatorHuggingFace Daily Papers7/24, 12:00 PMnot independentRepresentative
    FinanceComplexQA: Benchmarking Agentic Reasoning on Industrial-grade Financial Documents