A Dynamic Approach to Collaborative Document Writing

2025-08-24

AI Summary

This paper addresses the mechanism design problem for multi-agent collaborative authoring of unordered paragraph-set documents. We propose a cooperative framework integrating LLM-driven paragraph generation, context-aware voting, and dynamic text aggregation, formally modeling strategic interactions among agents under asynchronous proposal and collective selection. Theoretically, we characterize a fundamental trade-off between stability and social welfare, and prove that the mechanism achieves rapid convergence under realistic assumptions. Agent-based simulations demonstrate that, compared to baseline approaches, our framework attains stable document states with higher social welfare in fewer rounds, while exhibiting robustness to agent heterogeneity and initial disagreement. Our core contribution lies in the first unified treatment of mechanism design, NLP-based semantic modeling, and multi-agent consensus dynamics within the setting of unordered textual collaboration.

Technology Category

• Multiagent Systems: Mechanism Design
• Game Theory and Economic Paradigms: Mechanism Design
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Agentic search

Abstract

We introduce a model for collaborative text aggregation in which an agent community coauthors a document, modeled as an unordered collection of paragraphs, using a dynamic mechanism: agents propose paragraphs and vote on those suggested by others. We formalize the setting and explore its realizations, concentrating on voting mechanisms that aggregate votes into a single, dynamic document. We focus on two desiderata: the eventual stability of the process and its expected social welfare. Following an impossibility result, we describe several aggregation methods and report on agent-based simulations that utilize natural language processing (NLP) and large-language models (LLMs) to model agents and their contexts. Using these simulations, we demonstrate promising results regarding the possibility of rapid convergence to a high social welfare collaborative text.

Problem

• Modeling collaborative document writing through agent voting
• Exploring stability and social welfare in dynamic text aggregation
• Using NLP and LLMs to simulate agent-based collaborative writing

Innovation

• Dynamic voting mechanism for collaborative writing
• NLP and LLM for agent-based simulations
• Aggregation methods ensuring stability and welfare