Diverse Content Generation using Verbalized Sampling

Overview

This skill teaches agents how to use Verbalized Sampling (VS) - a research-backed prompting technique that dramatically increases output diversity (1.6-2.1× improvement) without sacrificing quality.

The Problem: Standard aligned LLMs suffer from "mode collapse" - they generate overly similar, safe, predictable outputs because of typicality bias in training data.

The Solution: Instead of asking for single instances ("write a blog post"), VS prompts the model to verbalize a probability distribution over multiple responses ("generate 5 blog post ideas with their probabilities").

Core Principle: Different prompt types collapse to different modes. Distribution-level prompts recover the diverse base model distribution, while instance-level prompts collapse to the most typical output.

Workflow Decision Tree

Detect user intent, route to appropriate reference:

| User Request Pattern | Route To | Description |