← back
arXivMuhammad Usman Safder, Ayesha Gull, Rania Elbadry, Fan Zhang, Yankai Chen, Xueqing Peng, Xue, Liu, Preslav Nakov, Zhuohan XieTue, Jun 30, 2026, 4:33 AM PDT
score 16.6

LLMs lose their instructions over time in financial simulations

Original: FinPersona-Bench: A Benchmark for Longitudinal Psychometric Stability of Autonomous Financial Agents

Source: arxiv.org

Writing ELI5 summary…