New Accounting Graph Transformer enables joint 12-month forecasting of 13 financial KPIs from limited accounting history, addressing a core pain point for small business planning and risk workflows.
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 ...
arXiv paper argues top-k embedding retrieval fails on financial statements and audit reports; proposes interpretable agentic operations for structured financial document analysis.
Researchers introduce FinReportBench, an expert-grounded benchmark measuring LLM-generated financial report quality for institutional use, identifying gaps in identity, compliance, sourcing, and vi...
FRAMES framework helps LLM agents improve at policy-bound tasks like document auditing by evolving skills from existing assets while preserving auditability and rule consistency—addressing the chal...
Academic paper proposes optimal allocation strategy for auditing LLM agent fleets with limited human budget, identifying miscalibration thresholds where confidence-based auditing underperforms rand...
Research on 99,952 examples shows correct domain rubrics improve LLM evaluator accuracy by 2.11 points, suggesting specialization matters more in evaluation rules than model weights.
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...
Researchers propose Hierarchical Reranker, a RAG framework designed to improve how AI systems retrieve and analyze large-scale financial documents like 10-K filings and tabular disclosures, address...
Mercor and Ramp launch APEX-Accounting, a 160-task benchmark evaluating whether frontier AI models can perform core accounting work like reconciliation, accrual, transaction posting, and reporting.
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...
German tax advisory firm HSP GRUPPE uses ChatGPT Enterprise to boost productivity and capacity in tax services, improving work quality and client delivery.
Isaac Perdomo from Opzer walks accounting professionals through first-time Claude setup and use cases for automating accounting firm workflows in a 60-minute hands-on workshop.
Snowflake introduces agentic intelligence system for contract review that detects novel clauses using semantic analysis beyond rule-based patterns, combining known-standard language detection with ...
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 ...
Intuit expands QuickBooks integrations with Claude and ChatGPT to enable agentic tasks—creating invoices, checking payroll data, and accessing lending benchmarks—moving beyond read-only access to a...
Sam Leon, founder of The Millennial CPA, shares how Claude projects automate document processing and workpaper generation, reducing tax prep time 5x while revealing review as the persistent bottlen...
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.
Billtrust connects its AR platform to Claude and Microsoft Copilot, allowing AI agents to access structured invoice data with audit trail tracking but no raw data exposure.
Accounting firm leaders are using Claude and LLMs to build custom audit and financial reporting tools for under $30K, replacing $200K–$300K annual vendor quotes, but Blake Oliver warns of hidden co...