Recent advances in large language models (LLMs) promise to facilitate the creation of synthetic agents that simulate realistic human behaviors, offering social sciences an ethical and scalable alternative to experiments with individuals. Whether such agents can faithfully capture psychological differences driven by personality traits, however, remains an open question. We evaluate the capacity of LLM agents, conditioned on Big-Five profiles, to reproduce personality-based variation in susceptibility to misinformation, focusing on news discernment, the ability to judge true headlines as true and false headlines as false. We observe that LLM agents are able to simulate human-like associations between personality traits and susceptibility to misinformation for socially desirable traits (Agreeableness, Conscientiousness, Open-Mindedness), but diverge for less desirable traits. The results underscore both the promise and the limits of personality-aligned LLMs for online human behavioral simulation.