Fig.1

Concept

Single-pass code

Single-pass code is an agent design where a model writes one complete program up front, then runs it and reads the result, with no chance to inspect intermediate values while writing. The model commits to the full script before seeing any output.

The rest of “Single-pass code” is a premium feature: every concept in the library gets a precise, practitioner-focused write-up like this one, cross-linked straight from the paper summaries that use it.

Log in to unlock

← Back to the library