VII · Verification & ReflectionEmerging★

Generator-Critic Separation

also known as Strict Generator-Critic Roles, Separated-Roles Critique

Strict role separation between a Generator agent that produces drafts and a Critic agent that judges them against pre-defined criteria; the Critic never generates.

This pattern helps complete certain larger patterns —

  • specialisesReflection★★— Have the model review its own output and produce a revised version in one or more passes.

Context

A team adopts a critique workflow. The same model is often given both roles in turn ('now generate', 'now critique'), or the critic is allowed to suggest revisions (mixing critique and generation). The result is inconsistent role discipline.

Problem

When the critic can generate, it tends to rewrite rather than name issues, depriving the team of clean error signals. When the same model swaps roles, biases bleed across the swap. The team cannot tell whether the critic caught a real issue or invented an opinion. Differs from inner-critic (same model), llm-as-judge (judge-only with no revision loop), and reflection (which subsumes both roles).

Forces

  • Single-model role-swap is cheaper than two separate models.
  • Letting the critic rewrite is faster than separating critique from revision.
  • Role separation requires architectural enforcement, not just prompt instructions.

Example

A press-release agent has Generator (drafts) and Critic (judges against a rubric: tone-on-brand, no banned phrases, all facts cited). Critic returns {findings: [{section: para3, issue: missing-citation, severity: high, citation: rule-7}]}. Generator revises only those flagged sections. The Critic never wrote prose; its only output was structured findings. Audit can count finding rate per rule.

Diagram

Solution

Therefore:

Generator and Critic are separate components (different model calls; ideally different model instances). Critic's interface returns structured findings: list of {section, issue_class, severity, citation}. Critic cannot produce free-form text or rewrites. On non-empty findings, findings are passed back to Generator which produces a revision. Pair with cross-reflection, frozen-rubric-reflection, llm-as-judge.

What this pattern forbids. Generator may not critique; Critic may not generate or rewrite; the only output the Critic produces is structured findings.

The smaller patterns that complete this one —

  • generalisesPipeline Triad Pattern★— Staff each pipeline stage with a triad — Creator generates an artifact, Critic finds flaws, Arbiter makes a binding PASS/FAIL/PARTIAL decision — with four explicit human gates between stages.

And the patterns that stand alongside it, or against it —

  • alternative-toSelf-Modification Diff Gate·— Gate the agent's edits to its own code or rules through a separate critic persona that reviews the diff before it lands.
  • complementsLLM-as-Judge★★— Use an LLM to score open-ended outputs against rubric criteria when no exact-match metric applies.
  • complementsCross-Reflection★— Reflection step performed by a *different* agent or foundation model from the original generator, so critique error is decorrelated from generation error.
  • complementsFrozen Rubric Reflection★— Constrain reflection to a fixed, hand-authored rubric of criteria so the reviewer cannot invent new ones each run.

Neighbourhood

Click any neighbour to follow the language. Scroll to zoom, drag to pan.

References

Provenance