# WINELL: Wikipedia Never-Ending Updating with LLM Agents

arXiv: https://arxiv.org/abs/2508.03728 · HTML: https://mlsanity.com/paper/2508.03728/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Placed in Web, search, and research agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 45 references that are in the map.
- First posted on arXiv 30 Jul 2025.

## Placed in

- LLM agents and tool use / [Web, search, and research agents](https://mlsanity.com/agents/web-search-and-research-agents/)

## Builds on (most cited first, 16 of 16)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [BrowseComp: A Simple Yet Challenging Benchmark for Browsing Agents](https://mlsanity.com/paper/2504.12516/) (2025)
- [Multi-Agent Collaboration Mechanisms: A Survey of LLMs](https://mlsanity.com/paper/2501.06322/) (2025)
- [MiniCheck: Efficient Fact-Checking of LLMs on Grounding Documents](https://mlsanity.com/paper/2404.10774/) (2024)
- [Fact, Fetch, and Reason: A Unified Evaluation of Retrieval-Augmented Generation](https://mlsanity.com/paper/2409.12941/) (2024)
- [Assisting in Writing Wikipedia-like Articles From Scratch with Large Language Models](https://mlsanity.com/paper/2402.14207/) (2024)
- [MindSearch: Mimicking Human Minds Elicits Deep AI Searcher](https://mlsanity.com/paper/2407.20183/) (2024)
- [Automatic Fact-guided Sentence Modification](https://mlsanity.com/paper/1909.13838/) (2019)
- [Infogent: An Agent-Based Framework for Web Information Aggregation](https://mlsanity.com/paper/2410.19054/) (2024)
- [WikiContradiction: Detecting Self-Contradiction Articles on Wikipedia](https://mlsanity.com/paper/2111.08543/) (2021)
- [Citation Needed: A Taxonomy and Algorithmic Assessment of Wikipedia's Verifiability](https://mlsanity.com/paper/1902.11116/) (2019)
- [Finding News Citations for Wikipedia](https://mlsanity.com/paper/1703.10339/) (2017)
- [Automated News Suggestions for Populating Wikipedia Entity Pages](https://mlsanity.com/paper/1703.10344/) (2017)
- [Level-Navi Agent: A Framework and benchmark for Chinese Web Search Agents](https://mlsanity.com/paper/2502.15690/) (2024)
- [Bots vs. Wikipedians, Anons vs. Logged-Ins](https://mlsanity.com/paper/1402.0412/) (2014)

## Built on by (most cited first, 5 of 5)

- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [When Benchmarks Age: Temporal Misalignment through Large Language Model Factuality Evaluation](https://mlsanity.com/paper/2510.07238/) (2025)
- [RADAR: Defending RAG Dynamically against Retrieval Corruption](https://mlsanity.com/paper/2605.22041/) (2026)
- [Who Maintains Agent Skills? A Longitudinal Study of Human-Governed, AI-Assisted Skill Maintenance](https://mlsanity.com/paper/2609.05677/) (2026)
- [Knowledge Pull Requests for Continual Document Authoring](https://mlsanity.com/paper/2609.26634/) (2026)

## Abstract (arXiv)

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.