CLQT: A Closed-Loop, Cost-Aware, Strategy-Consistent Benchmark for Diagnostic Evaluation of LLM Portfolio-Management Agents
The CLQT benchmark provides a diagnostic way to evaluate LLM portfolio-management agents beyond simple profit metrics. Using the APM-CS scorecard, it assesses reasoning coherence, signal acuity, and technical reliability. The discussion highlights the Coherence Gap and how using structured agent committees can prevent logic collapses.