In a dynamic, multiagent environment, an automated intelligent agent i
s often faced with the possibility that other agents may instigate eve
nts that hinder or help the achievement of its own goals. To act intel
ligently in such an environment, an automated agent needs an event tra
cking capability to continually monitor the occurrence of such events
and the temporal relationships among them. This capability enables an
agent to infer the occurrence of important unobserved events as well a
s to obtain a better understanding of the interaction among events. Th
is article focuses on event tracking in one complex and dynamic multia
gent environment: the air-combat simulation environment. It analyzes t
he challenges that an automated pilot agent must face when tracking ev
ents in this environment. This analysis reveals three new issues that
have not been addressed in previous work in this area: (i) tracking ev
ents generated by agents' flexible and reactive behaviors, (ii) tracki
ng events in the context of continuous agent interactions, and (iii) t
racking events in real time. This article proposes one solution to add
ress these issues. One key idea in this solution is that the (architec
tural) mechanisms that an agent employs in generating its own flexible
and reactive behaviors can be used to track other agents' flexible an
d reactive behaviors in real time. A second key idea is the use of a w
orld-centered representation for modeling agent interactions. The solu
tion is demonstrated using an implementation of an automated pilot age
nt.