New scattering layer called Deposon makes LLM multi-step reasoning auditable by binding each reasoning node to a conserved state, enabling machine-checkable verification of discarded reasoning path...
OntoKG-EQ addresses the audit and reproducibility crisis in equity analysis by replacing ad-hoc spreadsheets with a provenance-grounded knowledge graph that links analyst queries to evidence, times...
Researchers propose event-to-action process mining framework enabling AI agents to evaluate proposed actions against organizational controls, risk, and authority—extending traditional process minin...
Researchers propose VST, a typed messaging protocol for AI agents that creates verifiable, replayed audit trails in financial alpha discovery workflows, addressing traceability gaps in LLM-based mu...
Researchers propose SerenAI, an LLM-based state-transition system that outputs auditable, verifiable predictions instead of unconstrained text—addressing the need for traceable AI in legal, financi...
Probity benchmark reveals LLMs give inconsistent answers on identical accounting queries 60+ times; researchers identify systematic defect where evidence is hidden from model's visible context window.
Researchers release FinRAG-QA, a 999-question benchmark dataset for AI systems to answer questions about banks' financial statements, addressing the complexity of comparative analysis across jurisd...
Academic paper introduces ensemble margin and local prediction variability metrics to audit decision systems affected by predictive multiplicity (Rashomon effect), enabling better human review rout...
New 8B-parameter LLM VERA-8B identifies audit risks in SEC filings with evidence-grounded reasoning, addressing the gap between general financial language models and audit-specific requirements for...
Researchers propose architecture pattern separating LLM agent personas from execution to maintain audit trails while allowing instruction evolution—key for deploying AI agents in governed organizat...
Pre-registered research reveals that the dominant statistical method for auditing LLM judges—difference-in-differences on rating scales—produces spurious findings due to censoring effects that conf...
TrustNotch introduces verifiable, offline audit logging for AI agents, enabling auditors to detect tampering and verify agent behavior without relying on centralized systems—critical for regulatory...
Developer launched an AI auditing system using 7 agents that scored their own startup at 34/100 and caught revenue over-crediting; delivered scored PDF reports in hours for $98, demonstrating trans...
ICAEW survey reveals audit firms underutilize analytics software, defaulting to manual sampling instead—a trust gap that limits AI/automation adoption in external audit.
DataSnipper showcases how prebuilt AI agents can automate routine revenue audit procedures, reducing manual testing burden for external auditors.
Legora deployed GPT-6 Astra to review 41 financial documents in minutes, catching all planted errors and boosting performance by 40% in a document-review workflow.
Major accounting firms still unable to reliably prevent AI hallucinations in financial tasks, raising risks for audit quality and client trust.
Cherry Hill Advisory debuts AI agent-powered external quality assessments (EQAs), automating quality review processes for accounting firms with AI-led teams.
RSM and Andera partner to launch Beacon, an AI-driven control testing platform for internal auditors, bringing agentic automation to a core audit function.
AuditFile releases agentic AI orchestrator suite treating AI agents and human auditors as interchangeable team members within engagements.