New audit framework tests LLM agents' ability to diagnose blocked tasks

Verifiable data-analytic agents improve auditability of LLM reasoning

HQ arXiv: AI + Accounting arXiv · 3d ago · 1 min read

Researchers propose VeriGraph, a framework to make LLM-based agents' outputs auditable by separating deterministic data computations from semantic reasoning, addressing a key challenge for accounti...

Audit checklists for AI coding agents proposed across languages

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

Software engineer proposes 30-item audit checklist for validating AI-generated code across programming languages, addressing quality and safety concerns in agent-driven development.

New Framework Secures AI Agents Controlling Production Accounting Systems

arXiv: AI + Accounting arXiv · 8d ago · 1 min read

Researchers propose Sovereign Assurance Boundary (SAB), a certificate-based control system for AI agents managing high-stakes financial infrastructure, addressing audit and authorization gaps in no...

Trace2Policy: AI agents learn audit rules from expert behavior traces

HQ arXiv: AI + Accounting arXiv · 9d ago · 1 min read

Researchers introduce Trace2Policy, an AI system that extracts tacit decision rules from audit and compliance experts, then iteratively refines them through error analysis—automating expert judgmen...

DuMate-DeepResearch system tackles auditable multi-agent reasoning for comple...

HQ arXiv: AI + Accounting arXiv · 13d ago · 1 min read

New multi-agent framework DuMate-DeepResearch addresses hallucination and verification challenges in deep research tasks through recursive search and rubric-grounded reasoning, with direct applicat...