# arstanley/awesome-llm-conversation-simulation architecture

> Architecture diagram of the GitHub repository arstanley/awesome-llm-conversation-simulation, generated by GitDiagram from its file tree, README and a sample of source files (last updated 2026-09-30). It is an AI-made overview: check details against the source.

- Interactive diagram: https://gitdiagram.com/arstanley/awesome-llm-conversation-simulation
- Repository: https://github.com/arstanley/awesome-llm-conversation-simulation

## Overview

This repository is a curated survey companion, not a runnable simulator: it organizes papers, taxonomies, and benchmarks for LLM-based conversational user simulation. The reader-facing workflow is to consult the survey’s taxonomy, browse research by simulation target, interaction setting, or technique, and then explore related evaluation, datasets, applications, and open problems. The README documents these topics but no implementation or links between individual research entries, so the graph represents only those documented relationships.

Main entry points: [`README.md`](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md) (Curated companion)

## Diagram (Mermaid)

```mermaid
flowchart TD

subgraph group_overview["Survey resource"]
  node_resource["Curated companion<br/>[README.md]"]
  node_survey["Survey paper"]
end

subgraph group_taxonomy["Simulation taxonomy"]
  node_taxonomy_overview["Three-axis taxonomy<br/>[README.md]"]
  node_targets["Simulation targets<br/>[README.md]"]
  node_general["General user<br/>[README.md]"]
  node_persona["Persona-level<br/>[README.md]"]
  node_roleplay["Role-play<br/>[README.md]"]
  node_individual["Individual user<br/>[README.md]"]
  node_hybrid["Hybrid simulation<br/>[README.md]"]
  node_settings["Interaction settings<br/>[README.md]"]
  node_methods["Technical approaches<br/>[README.md]"]
  node_techniques["Prompting, RAG, training<br/>[README.md]"]
end

subgraph group_landscape["Research topics"]
  node_evaluation["Evaluation<br/>[README.md]"]
  node_datasets["Datasets<br/>[README.md]"]
  node_applications["Applications<br/>[README.md]"]
  node_problems["Open problems<br/>[README.md]"]
end

node_reader(("Research reader"))

node_reader -->|"browses"| node_resource
node_resource -->|"accompanies"| node_survey
node_resource -->|"organizes around"| node_taxonomy_overview
node_taxonomy_overview -->|"covers"| node_targets
node_taxonomy_overview -->|"covers"| node_settings
node_taxonomy_overview -->|"covers"| node_methods
node_targets -->|"includes"| node_general
node_targets -->|"includes"| node_persona
node_targets -->|"includes"| node_roleplay
node_targets -->|"includes"| node_individual
node_targets -->|"includes"| node_hybrid
node_methods -->|"includes"| node_techniques
node_resource -->|"lists"| node_evaluation
node_resource -->|"lists"| node_datasets
node_resource -->|"lists"| node_applications
node_resource -->|"lists"| node_problems

click node_resource "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"
click node_taxonomy_overview "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"
click node_targets "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"
click node_general "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"
click node_persona "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"
click node_roleplay "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"
click node_individual "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"
click node_hybrid "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"
click node_settings "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"
click node_methods "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"
click node_techniques "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"
click node_evaluation "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"
click node_datasets "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"
click node_applications "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"
click node_problems "https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md"

classDef toneNeutral fill:#f8fafc,stroke:#334155,stroke-width:1.5px,color:#0f172a
classDef toneBlue fill:#dbeafe,stroke:#2563eb,stroke-width:1.5px,color:#172554
classDef toneAmber fill:#fef3c7,stroke:#d97706,stroke-width:1.5px,color:#78350f
classDef toneMint fill:#dcfce7,stroke:#16a34a,stroke-width:1.5px,color:#14532d
classDef toneRose fill:#ffe4e6,stroke:#e11d48,stroke-width:1.5px,color:#881337
classDef toneIndigo fill:#e0e7ff,stroke:#4f46e5,stroke-width:1.5px,color:#312e81
classDef toneTeal fill:#ccfbf1,stroke:#0f766e,stroke-width:1.5px,color:#134e4a
class node_resource,node_survey toneBlue
class node_taxonomy_overview,node_targets,node_general,node_persona,node_roleplay,node_individual,node_hybrid,node_settings,node_methods,node_techniques toneAmber
class node_evaluation,node_datasets,node_applications,node_problems toneMint
class node_reader toneIndigo
```

## Components

### Survey resource

- [Curated companion](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`
- **Survey paper**

### Simulation taxonomy

- [Three-axis taxonomy](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`
- [Simulation targets](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`
- [General user](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`
- [Persona-level](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`
- [Role-play](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`
- [Individual user](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`
- [Hybrid simulation](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`
- [Interaction settings](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`
- [Technical approaches](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`
- [Prompting, RAG, training](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`

### Research topics

- [Evaluation](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`
- [Datasets](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`
- [Applications](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`
- [Open problems](https://github.com/arstanley/awesome-llm-conversation-simulation/blob/main/README.md): `README.md`

### Other components

- **Research reader**

## Connections

- Research reader → Curated companion: browses (evidence: `README.md`)
- Curated companion → Survey paper: accompanies (evidence: `README.md`)
- Curated companion → Three-axis taxonomy: organizes around (evidence: `README.md`)
- Three-axis taxonomy → Simulation targets: covers (evidence: `README.md`)
- Three-axis taxonomy → Interaction settings: covers (evidence: `README.md`)
- Three-axis taxonomy → Technical approaches: covers (evidence: `README.md`)
- Simulation targets → General user: includes (evidence: `README.md`)
- Simulation targets → Persona-level: includes (evidence: `README.md`)
- Simulation targets → Role-play: includes (evidence: `README.md`)
- Simulation targets → Individual user: includes (evidence: `README.md`)
- Simulation targets → Hybrid simulation: includes (evidence: `README.md`)
- Technical approaches → Prompting, RAG, training: includes (evidence: `README.md`)
- Curated companion → Evaluation: lists (evidence: `README.md`)
- Curated companion → Datasets: lists (evidence: `README.md`)
- Curated companion → Applications: lists (evidence: `README.md`)
- Curated companion → Open problems: lists (evidence: `README.md`)