用AI代理自动更新维基百科，保持知识实时准确。
WINELL: Wikipedia Never-Ending Updating with LLM Agents
- 构建多智能体系统，自动采集网络信息并筛选关键更新。
- 编辑模型覆盖率达92.3%，比GPT-4o更高效且贴近人工编辑风格。
- 适合研究知识库自动化维护与大模型代理应用的学者。
维基百科作为广泛使用的知识库，因依赖人工编辑难以及时更新。受NELL持续知识获取理念启发，本文提出WiNELL框架，利用基于大模型的智能体实现维基百科内容的持续更新。该框架通过多智能体协作，从网络中聚合信息，筛选目标实体的新且重要的知识，并生成符合人类编辑习惯的精准修改建议。基于维基百科历史编辑数据训练的细粒度编辑模型，使更新方式与人工行为一致。实验显示，其在关键信息覆盖率和编辑效率上均优于开源指令跟随模型及闭源模型（如GPT-4o）。端到端评估表明，该系统能有效识别并建议高活跃页面的时效性更新。这为大模型智能体在永续知识库维护中的应用开辟了新路径。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。