CODS 2025 AssetOpsBench reveals multi-agent orchestration patterns in industr...

AI document intelligence automates large-scale audit transaction testing

HQ arXiv: AI + Accounting arXiv · 1mo ago · 1 min read

Researchers present automated framework using Snowflake Document AI to extract structured data from millions of unstructured PDF statements, replacing labor-intensive manual audit sampling with sca...

OpenAI GPT-5.4 tops AI accounting benchmark at 77%, but reliability gaps persist

HQ Dual Entry Blog blogscraper · 3mo ago · 1 min read

DualEntry's benchmark tested 19 AI models on 101 accounting tasks; GPT-5.4 led with 77.3% accuracy but failed on roughly 1 in 4 real-world accounting workflows.

AI Models Fail One-Third of Real Accounting Tasks, Study Shows

HQ Dual Entry Blog blogscraper · 3mo ago · 1 min read

DualEntry Labs benchmarks AI models on actual accounting work, finding 66% accuracy and identifying critical gaps in autonomous finance capabilities.

Multi-agent systems automate IT-Grundschutz compliance audits for SMEs

HQ arXiv: AI + Accounting arXiv · 2d ago · 1 min read

Researchers propose probabilistic multi-agent systems to automate labor-intensive IT-Grundschutz audits under NIS-2 Directive, reducing manual documentation and validation burden for compliance.

Researcher audits 1B LLM tokens, exposes token compression billing discrepancy

HQ HN: Accounting & AI HN · 2d ago · 1 min read

An audit of 1 billion tokens reveals a major gap between token compression rates (99%) and actual billing, suggesting potential overcharges or token counting inconsistencies in LLM API pricing.