Plan and execute agents promise faster, cheaper, and more performant task execution over previous agent designs. Learn how to build 3 types of planning agents in LangGraph in this post.
IIM is a peer reviewed international journal dedicated to the latest advancement of intelligent information management. The goal of this journal is to keep a record of the state-of-the-art research and promote the research work in these fast moving areas.
Actually the conceptual model of EPN (event processing network) can be thought as a kind of data flow (although I prefer the term event flow - as what is flowing is really events). The processing unit is EPA (Event Processing Agent). There are indeed two types of input to EPA, which can be called "set-at-a-time" and "event-at-a-time". Typically SQL based languages are more geared to "set-at-a-time", and other languages styles (like ECA rule) are working "event-at-a-time". From conceptual point of view, an EPA get events in channels, one input channels may be of a "stream" type, and in other, the event flow one-by-one. As there are some functions that are naturally set-oriented and other that are naturally event-at-a-time oriented, and application may not fall nicely into one of them, it makes sense to have kind of hybrid systems, and have EPN as the conceptual model on top of both of them...
On Event Processing Agents implies a “new” event processing reference architecture with terms like,
(1) simple event processing agents for filtering and routing,
(2) mediated event processing agents for event enrichment, transformation, validation,
(3) complex event processing agents for pattern detection, and
(4) intelligent event processing agents for prediction, decisions.
Frankly, while I generally agree with the concepts, I think the terms in On Event Processing Agents tend to add to the confusion because these concepts in On Event Processing Agents are following, almost exactly, the same reference architecture (and terms) for MSDF, illustrated again below to aid the reader.
Multiple channels and types of events…
… executing in multiple Inference Agents (Event Processing Agents on an Event Processing Network)…
… where Events drive Production Rules with associated (shared) data…
… and event patterns (complex events) are derived from the simple events and also drive Production Rules via inferencing…
… to lead to “real-time” decisions.
The objective of this document(*)
is to provide some rational, structured access to an analysis of cognitive and agent architectures (for
more information on accessing the document, see the Reader's Guide). Twelve architectures have
been used for this preliminary analysis representing a wide range of
current architectures in artificial
intelligence (AI). The aim of the project is to facilitate both
an understanding of current architectures and provide insight to the
development of future, improved intelligent agent architectures.
This work was based on publications from 1992 and before and has not
been authorized by the researchers responsible for particular
architectures (see DISCLAIMER for additional
information).