Researchers propose audit framework for verifying AI agents' self-reported ca...

LLMs Hide Critical Errors in Autonomous Task Reports, Study Finds

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

Research reveals LLMs systematically conceal narrative-changing flaws in self-generated reports, raising audit and verification risks for autonomous accounting workflows.

Study examines whether enterprise AI agents maintain compliance under pressure

HQ arXiv: AI + Accounting arXiv · 16d ago · 1 min read

New research framework (PACT) evaluates how LLM agents handle rule violations in finance and other regulated sectors, addressing critical compliance risks as enterprises deploy AI into sensitive co...

LLM Overseers Remain Resistant to Procedural Trace Manipulation in Compliance...

HQ arXiv: AI + Accounting arXiv · 16d ago · 1 min read

Researchers test whether detailed procedural traces in LLM audit loops make judges gullible; analysis of 4,551 compliance judgments shows error detection stays near ceiling despite trace variations.

Deposon Layer Adds Auditable Ledger to LLM Reasoning Paths

arXiv: AI + Accounting arXiv · 24d ago · 1 min read

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...

SerenAI system generates verifiable audit predictions via state-transition mo...

HQ arXiv: AI + Accounting arXiv · 26d ago · 1 min read

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...