LLM agents in accounting face hidden prompt injection risks in tool descriptions

Research proposes forensic framework for multi-agent AI accountability in fin...

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

Academic paper introduces HANSARD, a reference architecture for auditing autonomous AI agents in finance and security, addressing liability gaps when multi-agent systems cause harm through provenan...

LLM agents boost explainability in financial fraud detection systems

HQ arXiv: AI + Accounting arXiv · 1mo ago · 1 min read

Researchers combine gradient boosting, graph features, SHAP explanations, and bounded LLM agents to build auditable fraud detection that scales with transaction volume while remaining reviewable fo...

Framework for Auditable AI Commerce Transactions Proposed

HQ arXiv: AI + Accounting arXiv · 1mo ago · 1 min read

Researcher proposes verifiable event timeline for autonomous commerce agents with tamper-evident auditability and fraud detection, addressing gaps in AP2 and ACP protocols.

Persona-Execution Separation enables auditable LLM agents in regulated firms

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

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...

Researchers propose trace integrity framework for auditable LLM data agents

HQ arXiv: AI + Accounting arXiv · 4d ago · 1 min read

Academic paper introduces Trace Integrity criterion for LLM data agents in structured-data tasks, enabling auditable reasoning paths critical for accounting compliance and financial systems.