Framework makes LLM-generated financial analysis auditable by design

Study audits self-evolving financial agents for security drift and capability...

HQ arXiv: AI + Accounting arXiv · 7d ago · 1 min read

Researchers audit three self-evolving financial AI agents (SkillOpt, AWM, ReasoningBank) in e-banking scenarios, finding that performance gains don't guarantee security preservation or behavioral c...

FinRank benchmark tests AI accuracy on SEC filing questions

HQ arXiv: AI + Accounting arXiv · 17d ago · 1 min read

New research introduces FinRank, a benchmark for evaluating AI systems on financial question answering over SEC filings, focusing on evidence provenance rather than answer correctness alone.

Multi-agent LLM pipelines may amplify audit bias despite review checks, study...

HQ arXiv: AI + Accounting arXiv · 18d ago · 1 min read

Research on role-differentiated LLM agents for audit resource allocation shows that distributing triage decisions across multiple agents can paradoxically worsen demographic bias outcomes compared ...

Researchers propose agentic retrieval for financial documents over traditiona...

HQ arXiv: AI + Accounting arXiv · 18d ago · 1 min read

arXiv paper argues top-k embedding retrieval fails on financial statements and audit reports; proposes interpretable agentic operations for structured financial document analysis.

Audit Framework Reveals AI Evidence Decay in Accounting Research

HQ arXiv: AI + Accounting arXiv · 29d ago · 1 min read

Researcher audits 40 empirical records on generative AI in accounting, finding that model obsolescence and publication lag create systematic validity gaps—proposing a claim-currency framework to as...