Event-sourced architecture enables auditable AI agent systems

New Protocol Enables Portable Testing for AI Agents Across Frameworks

HN: Accounting & AI HN · 6d ago · 1 min read

ECP introduces vendor-neutral standard for evaluating AI agent outputs and tool calls with audit-visible context, enabling consistent testing across models and CI systems.

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

HQ arXiv: AI + Accounting arXiv · 12d 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.

Neurosymbolic Framework Bridges LLM Flexibility and Business Process Auditabi...

HQ arXiv: AI + Accounting arXiv · 15d ago · 1 min read

VADAOrchestra combines LLM-based agentic reasoning with symbolic logic to enable adaptive, auditable decision-making in business processes—addressing a core tension in AI-driven accounting workflows.

Multi-agent pipeline brings auditable AI to financial chart analysis

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

AgentFinVQA combines on-premise deployability with auditability for financial chart QA, addressing regulated auditors' need for explainable AI without accuracy compromise.

Verifiable data-analytic agents improve auditability of LLM reasoning

HQ arXiv: AI + Accounting arXiv · 21d 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...