We present a framework for Bayesian updating of beliefs about models o
f agent(s) based on their observed behavior. We work within the formal
ism of the Recursive Modeling Method (RMM) that maintains and processe
s models an agent may use to interact with other agent(s), the models
the agent may think the other agent has of the original agent, the mod
els the other agent may think the agent has, and so on. The beliefs ab
out which model is the correct one are incrementally updated based on
the observed behavior of the modeled agent and, as the result, the pro
bability of the model that best predicted the observed behavior is inc
reased. Analogously, the models on deeper levels of modeling can be up
dated; the models that the agent thinks another agent uses to model th
e original agent are revised based on how the other agent is expected
to observe the original agent's behavior, and so on. We have implement
ed and tested our method in two domains, and the results show a marked
improvement in the quality of interactions with the belief update in
both domains.