Research on multi-agent protocols for operational AI in regulated workflows

Researchers propose irreversibility budget to manage fleet-level AI agent risks

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

Academic paper proposes cumulative risk-accounting framework for LLM agent fleets to prevent overdrawing principals' risk tolerance across workflows, addressing gaps in current per-agent authorizat...

Semi-Structured Regression Model Balances Credit Risk Prediction With Audit T...

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

Researchers introduce findr, a machine learning framework that combines predictive accuracy with interpretable credit risk decisions and fairness constraints for regulatory compliance.

Generative AI inverts machine verification economics for autonomous systems

HQ arXiv: AI + Accounting arXiv · 17d ago · 1 min read

Researcher demonstrates single person directing fleet of AI agents via machine verification at scale, flipping traditional cost-overhead model where verification becomes essential productivity safe...

SENTRY replaces subjective questionnaires with deterministic ML for financial...

HQ arXiv: AI + Accounting arXiv · 17d ago · 1 min read

Researchers present SENTRY, a deterministic ML pipeline that automates risk assessment for IT changes in financial institutions, replacing error-prone self-reported questionnaires with auditable, c...

Benchmark reveals agentic AI models fail repeatedly at accounting tasks

HQ arXiv: AI + Accounting arXiv · 23d ago · 1 min read

AgentRelBench, a new reliability framework, tested nine LLM models on accounting operations and found systematic failures in irreversible tasks—exposing that single-run audits miss critical agent d...