# Chat-crowd: A Dialog-based Platform for Visual Layout Composition

## TL;DR

Chat-crowd is an interactive dialog-based platform enabling visual layout design through conversational interactions, supporting multi-agent collaboration, integration with crowdsourcing, and quality control for spatial reasoning tasks.

## Contribution

It introduces a novel conversational environment for visual layout composition with multi-agent roles and crowdsourcing integration, facilitating multimodal dialog research.

## Key findings

- Supports multiple conversational roles for design and directive tasks.
- Integrates with crowdsourcing platforms for data collection.
- Includes quality control mechanisms for agent performance.

## Abstract

In this paper we introduce Chat-crowd, an interactive environment for visual layout composition via conversational interactions. Chat-crowd supports multiple agents with two conversational roles: agents who play the role of a designer are in charge of placing objects in an editable canvas according to instructions or commands issued by agents with a director role. The system can be integrated with crowdsourcing platforms for both synchronous and asynchronous data collection and is equipped with comprehensive quality controls on the performance of both types of agents. We expect that this system will be useful to build multimodal goal-oriented dialog tasks that require spatial and geometric reasoning.