Polymind: Parallel Visual Diagramming with Large Language Models to Support Prewriting Through Microtasks

2025-02-13

AI Summary

Traditional pre-writing approaches relying on sequential LLM dialogues suffer from low ideation customization and poor efficiency. Method: This paper proposes a parallel multi-agent micro-task framework supporting visual, diagrammatic collaboration. The system integrates multiple LLM agents, a visual diagramming interface, a fine-grained micro-task orchestration engine, and a dynamic state management mechanism—enabling users to customize task logic, visibility, and agent proactivity. Contribution/Results: It is the first work to introduce collaborative group paradigms into the pre-writing stage, overcoming the limitations of single-turn prompting by enabling task-level parallelism and real-time visual feedback. Experiments demonstrate significant improvements over ChatGPT in ideation breadth, personalization depth, and idea expansion speed, leading to enhanced pre-writing efficiency and expressive diversity.

Technology Category

• Machine Learning: Large Multimodal Models (LMMs)
• Multiagent Systems: Coordination and Collaboration
• Cognitive Modeling & Cognitive Systems: Computational Creativity

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

Abstract

Prewriting is the process of generating and organising ideas before a first draft. It consists of a combination of informal, iterative, and semi-structured strategies such as visual diagramming, which poses a challenge for collaborating with large language models (LLMs) in a turn-taking conversational manner. We present Polymind, a visual diagramming tool that leverages multiple LLM-powered agents to support prewriting. The system features a parallel collaboration workflow in place of the turn-taking conversational interactions. It defines multiple ``microtasks'' to simulate group collaboration scenarios such as collaborative writing and group brainstorming. Instead of repetitively prompting a chatbot for various purposes, Polymind enables users to orchestrate multiple microtasks simultaneously. Users can configure and delegate customised microtasks, and manage their microtasks by specifying task requirements and toggling visibility and initiative. Our evaluation revealed that, compared to ChatGPT, users had more customizability over collaboration with Polymind, and were thus able to quickly expand personalised writing ideas during prewriting.

Problem

• Enhance prewriting with visual diagramming
• Facilitate parallel collaboration with LLMs
• Support microtasks for group brainstorming

Innovation

• Parallel visual diagramming tool
• Multiple LLM-powered agents
• Customizable microtasks orchestration