Agent Simulation

If you put a large language model in a classroom for a year, what kind of student would it become? According to Simulating Human-Like Learning Dynamics with LLM-Empowered Agents, the answer isn’t flattering: most base LLMs act like “diligent but brittle surface learners”—hardworking, seemingly capable, but unable to generalize deeply. From Psych Lab to AI Lab Educational psychology has spent decades classifying learners into profiles like deep learners (intrinsically motivated, reflective, conceptual) and surface learners (extrinsically motivated, test-oriented, shortcut-prone). The authors built LearnerAgent, a multi-agent framework grounded in these theories, and dropped four AI ‘students’ into a simulated high school English class: ...

“I think the next year’s Turing test will truly be the one to watch—the one where we humans, knocked to the canvas, must pull ourselves up… the one where we come back. More human than ever.” — Brian Christian (author of The Most Human Human) The AI Masquerade: Why Personality Now Wins the Game Artificial intelligence is no longer confined to tasks of logic or data wrangling. Today’s advanced language models have crossed a new threshold: the ability to convincingly impersonate humans in conversation. A recent study found GPT-4.5, when given a carefully crafted prompt, was judged more human than actual humans in a Turing test (Jones & Bergen, 2025). This result hinged not simply on technical fluency, but on the generation of believable personality—a voice that shows emotion, adapts to social context, occasionally makes mistakes, and mirrors human conversational rhythms. ...