Ask WhAI:Probing Belief Formation in Role-Primed LLM Agents
This work addresses the challenge of studying belief formation and epistemic silos in multi-agent scientific reasoning, offering a reproducible method for researchers in AI and cognitive science, though it is incremental as it builds on existing multi-agent and simulation frameworks.
The researchers tackled the problem of understanding belief formation in multi-agent interactions by developing Ask WhAI, a framework for inspecting and perturbing belief states, and applied it to a medical case simulator, revealing that agent beliefs often mirror real-world disciplinary stances with overreliance on canonical studies and resistance to counterevidence.
We present Ask WhAI, a systems-level framework for inspecting and perturbing belief states in multi-agent interactions. The framework records and replays agent interactions, supports out-of-band queries into each agent's beliefs and rationale, and enables counterfactual evidence injection to test how belief structures respond to new information. We apply the framework to a medical case simulator notable for its multi-agent shared memory (a time-stamped electronic medical record, or EMR) and an oracle agent (the LabAgent) that holds ground truth lab results revealed only when explicitly queried. We stress-test the system on a multi-specialty diagnostic journey for a child with an abrupt-onset neuropsychiatric presentation. Large language model agents, each primed with strong role-specific priors ("act like a neurologist", "act like an infectious disease specialist"), write to a shared medical record and interact with a moderator across sequential or parallel encounters. Breakpoints at key diagnostic moments enable pre- and post-event belief queries, allowing us to distinguish entrenched priors from reasoning or evidence-integration effects. The simulation reveals that agent beliefs often mirror real-world disciplinary stances, including overreliance on canonical studies and resistance to counterevidence, and that these beliefs can be traced and interrogated in ways not possible with human experts. By making such dynamics visible and testable, Ask WhAI offers a reproducible way to study belief formation and epistemic silos in multi-agent scientific reasoning.