AI & LLM

An agent is a digital actor that can perceive, decide, and act.

An Agent Profile describes who the agent is when the simulation starts.

ABM is a simulation where many agents interact so we can study what happens to the whole system.

CSR is a way of storing only the useful parts of a sparse matrix while remembering where those parts belong.

“A waiting line that decides which event happens next.”

External Status describes what can be observed about an agent's position and relationships.

A graph is a way of representing things as nodes and the relationships between those things as edges.

Internal Status is what is currently happening inside the agent and can change over time.

Knowledge distillation is teaching a small model to behave like a big model by learning from the big model's outputs.

A matrix is basically a 2D array where the row and column positions give meaning to each value.

MoM is like a smart dispatcher that sends each job to the cheapest system capable of handling it.

Prompt caching means “we've already solved this, so reuse the previous result.”

SimOps are the simulation's collection of specialized functions, with each function responsible for a different job needed to run the simulation.

State Transition is the rule that says: “When this event happens, change the current state in this particular way.”

A surrogate model is a smaller model that learned to handle the routine jobs normally handled by a much bigger model.

Instead of making the computer handle 10,000 similar jobs one by one, give it the 10,000 jobs together so it can process them in parallel.