Fixed computation
Every request follows roughly the same computational path. Cost and latency are predictable.
Layer 4 — Model Architecture · Chapter 4
Many early language models generated an answer in one continuous pass. More capable systems allocate additional computation to difficult problems, examine intermediate steps, use tools, test alternatives, or revise an initial result. This is often called test-time computation or inference-time scaling.
Prediction asks what is likely to come next. Planning asks which sequence of actions is most likely to reach a goal. A planning architecture usually needs a representation of the current state, possible actions, constraints, expected consequences, and a way to compare future paths.
When a problem has a checkable answer, architecture can separate generation from evaluation. One component proposes solutions; another tests them. Search may explore trees, graphs, programs, or simulated trajectories. Verification can be learned, rule-based, or performed by an external tool.
A system may answer an easy question quickly and spend much more computation on a difficult one. This creates a new design variable: not only how large the model is, but how much thinking it performs for each task.
Every request follows roughly the same computational path. Cost and latency are predictable.
The system spends more effort when uncertainty, complexity, or risk is high.
More computation can improve an answer, but architecture must decide where to spend it, how to test it, and when to stop.