liveBook · Manning

Measure-change-measure cycle

As explained in Self-Improving Agents

A recurring process of measuring an agent's output, finding an improved version, and submitting it.

A measure–change–measure cycle improves an agent by comparing its output with a standard, seeking a better version, and keeping the winner. Repeated search can update the agent and its harness without changing the underlying model. section 1.1.2 section 2.3.3

Each search pass has three moves:

  • Propose a variant of the current best. section 2.3.3
  • Measure the variant against the current best using the signal. section 2.3.3
  • Select the variant only if the signal prefers it, then repeat from the best candidate so far. section 2.3.3

From feedback to iteration

When a user reports a wrong answer, an engineer might inspect the conversation, edit the prompt, redeploy, and wait for more feedback. That manual loop is slow and human-gated; repeated search instead measures and selects among proposed variants. section 1.1.2 section 2.3.3

Figure 2.8 The search process. Search is the self-improvement loop run repeatedly: Propose generates a variant of the current best, Measure has the signal compare that variant against the current best, and Select applies the verdict, keeping the variant only when the signal preferred it. The signal does its work in Measure; Select is just the decision rule, with no second call to the signal. After the rounds run out, the best candidate becomes the new artifact.

Trace how proposal, measurement, and selection repeat until the remaining candidate becomes the new artifact. section 2.3.3

How Self-Improving Agents covers it

How deep it goes
Defines a propose–measure–select loop and repeats it until rounds end, without detailing how the measurement signal is constructed.
Examples
Contrasts a production fix prompted by user feedback with repeated candidate variants measured and selected.
What you can do after
Evaluate/understand candidate artifacts by comparing them with the current best and retaining the preferred variant.
How it connects
Connects agent improvement with prompt and context edits, evaluation signals, search, and agent harnesses.

Also explained in

Compare how 2 books explain measure-change-measure cycle →

Related concepts

This explainer was generated by Manning's knowledge graph from the text of Self-Improving Agents. The section links point to the parts of the book it draws on.