VII · Verification & ReflectionEmerging★

Human Reflection

also known as Human-Critique-In-Reflection-Loop, Human-Feedback Refinement

Reflection loop that explicitly collects human feedback (not approval) on agent plans to improve them, distinct from approval gates where the human only says yes/no.

This pattern helps complete certain larger patterns —

  • specialisesHuman-in-the-Loop★★— Require explicit human approval at defined points before the agent performs an action.
  • specialisesReflection★★— Have the model review its own output and produce a revised version in one or more passes.

Context

A team has an agent that produces plans, drafts, or analyses. Human-in-the-loop is in place but limited to approving or rejecting the final output. Humans see the output but cannot easily inject critique that the agent must act on.

Problem

Yes/no approval underuses the human's expertise. A reviewer often knows *why* something is wrong and could improve it with a suggestion, but the approval workflow has no channel for that suggestion to become an agent revision. The agent ships approved-but-imperfect outputs; the reviewer takes the burden of editing manually.

Forces

  • Pure approval workflows are simpler and faster than feedback loops.
  • Human feedback adds latency to the production cycle.
  • Feedback quality varies — agents must handle low-signal feedback gracefully.

Example

A research-summary agent produces a draft for a senior analyst. Instead of {approve, reject}, the UI shows the draft with a critique widget. Analyst writes 'the methodology section omits the control group'. The agent ingests the critique and emits a revised draft. Three rounds. The third draft is approved. The captured critiques feed a quarterly rubric update.

Diagram

Solution

Therefore:

Render agent output to the human with a structured feedback widget (critique text + optional structured fields like 'wrong section', 'missing claim'). On submit, the agent ingests the feedback as a critique and produces a revision. Loop until human approves OR loop budget exhausts. Differs from approval-queue (yes/no) and from human-in-the-loop (which subsumes both). Pair with reflection, frozen-rubric-reflection, approval-queue.

What this pattern forbids. The agent must treat human feedback as a critique input subject to revision, not as a binary signal; a loop budget caps the number of revision rounds.

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

  • alternative-toApproval Queue★★— Queue agent-proposed actions for asynchronous human review while the agent continues other work.
  • complementsFrozen Rubric Reflection★— Constrain reflection to a fixed, hand-authored rubric of criteria so the reviewer cannot invent new ones each run.
  • complementsEvaluator-Optimizer★★— One LLM generates; another evaluates and feeds back; loop until criteria are met.
  • complementsConfidence-Checking Workflow★— Always ask the agent, for each part of its output, to state its confidence and identify which parts need human verification, like triaging a junior analyst's work.
  • complementsCooperative Preference Inference·— Agent and human jointly optimise the human's reward without the agent being told what it is — the interaction is a two-player game in which alignment is learned while acting.

Neighbourhood

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

References

Provenance