AI RESEARCH
FinHarness: An Inline Lifecycle Safety Harness for Finance LLM Agents
arXiv CS.CL
•
ArXi:2605.27333v1 Announce Type: new Finance LLM agents must simultaneously block prompt-induced unauthorized actions and approve legitimate multi-step business workflows. However, boundary filters often miss irreversible mid-trajectory tool calls, while post-hoc LLM judges perform auditing only after termination -- too late for intervention and at a computational cost that scales linearly with trace length.