WINELL: Wikipedia Never-Ending Updating with LLM Agents

2025-07-30

AI Summary

Wikipedia faces challenges in content timeliness and update latency due to its reliance on manual editing. This paper proposes the first multi-LLM agent collaboration framework for continuous Wikipedia updating, enabling end-to-end generation of human-like editing suggestions—from knowledge discovery to stylistically appropriate revision—via a fine-grained edit model (trained on historical edit logs) and an information aggregation–importance filtering mechanism. Its key contributions are: (1) the first application of multi-agent collaboration to automated Wikipedia maintenance; and (2) simultaneous optimization of factual accuracy, linguistic naturalness, and editorial plausibility. End-to-end evaluation on highly active articles demonstrates that our system significantly outperforms GPT-4o and leading open-source instruction-tuned models in critical information coverage and editing efficiency. The framework provides a scalable, deployable automation pathway for sustainable knowledge base curation.

Technology Category

• Multiagent Systems: Coordination and Collaboration
• Machine Learning: Large Multimodal Models (LMMs)
• Natural Language Processing: Fact-Checking / Misinformation Detection (NLP Focus)

Application Category

• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

Wikipedia, a vast and continuously consulted knowledge base, faces significant challenges in maintaining up-to-date content due to its reliance on manual human editors. Inspired by the vision of continuous knowledge acquisition in NELL and fueled by advances in LLM-based agents, this paper introduces WiNELL, an agentic framework for continuously updating Wikipedia articles. Our approach employs a multi-agent framework to aggregate online information, select new and important knowledge for a target entity in Wikipedia, and then generate precise edit suggestions for human review. Our fine-grained editing models, trained on Wikipedia's extensive history of human edits, enable incorporating updates in a manner consistent with human editing behavior. Our editor models outperform both open-source instruction-following baselines and closed-source LLMs (e.g., GPT-4o) in key information coverage and editing efficiency. End-to-end evaluation on high-activity Wikipedia pages demonstrates WiNELL's ability to identify and suggest timely factual updates. This opens up a promising research direction in LLM agents for automatically updating knowledge bases in a never-ending fashion.

Problem

• Automating Wikipedia updates using LLM agents
• Improving content accuracy with multi-agent framework
• Enhancing editing efficiency via trained editor models

Innovation

• Multi-agent framework for Wikipedia updates
• Fine-grained editing models trained on human edits
• Outperforms GPT-4o in coverage and efficiency