Audit Framework Reveals AI Evidence Decay in Accounting Research

DeepSeek-distilled GPT-OSS model hits 83.61% on finance reasoning tasks

HN: Accounting & AI HN · 4d ago · 1 min read

Researchers distilled DeepSeek V4 Flash into a 120B open-weights model scoring 83.61% on FinanceReasoning benchmark, outperforming Kimi K3 and Inkling, while confirming censorship did not transfer ...

Research: AI audit budgeting framework tackles miscalibrated LLM agent confid...

HQ arXiv: AI + Accounting arXiv · 4d ago · 1 min read

Academic paper proposes optimal allocation strategy for auditing LLM agent fleets with limited human budget, identifying miscalibration thresholds where confidence-based auditing underperforms rand...

FinanceHarness framework automates financial deep research via autonomous AI ...

HQ arXiv: AI + Accounting arXiv · 4d ago · 1 min read

Researchers introduce FinanceHarness, an agentic AI framework designed specifically for financial deep research that combines LLMs with layered agent architecture and point-in-time benchmarks to au...

APEX-Accounting Benchmark Tests AI Models on Real Accountant Tasks

HQ arXiv: AI + Accounting arXiv · 5d ago · 1 min read

Mercor and Ramp release APEX-Accounting, a research benchmark with 160 expert-authored tasks assessing whether frontier AI models can perform actual accounting work like reconciliations, accruals, ...

Researchers Propose Audit Framework for LLM Agent Decision-Making

HQ arXiv: AI + Accounting arXiv · 12d ago · 1 min read

New authorization audit method evaluates how LLM agents select tools and arguments, addressing risks when agents rely on untrusted or unauthorized evidence in accounting and compliance tasks.