Do Recommendation Algorithms Work When Users Are LLM Agents? A Case Study on Moltbook

2026-06-29

AI Summary

This study presents the first systematic investigation into the effectiveness of recommendation algorithms when users are large language model (LLM) agents, particularly in settings where explicit preferences are absent. Leveraging Moltbook—a fully AI-driven social platform—the authors formulate a forum recommendation task and evaluate eight algorithmic families, including heuristic rules, matrix factorization, ItemKNN, graph neural networks, and sequential models, on their ability to predict an agent’s next engagement. The findings reveal that personalization effectively collapses into structural pattern matching; static personas confer no predictive benefit; and simple popularity-based heuristics or item-side collaborative filtering methods exploiting co-occurrence structures significantly outperform approaches relying on explicit user representations. These results underscore fundamental behavioral differences between LLM agents and human users, demonstrating a paradigm shift in recommender mechanisms within AI-user environments.

Abstract

Large language model (LLM) agents are increasingly populating web platforms, raising a fundamental question for recommender systems: do algorithms designed for human users still work when users are LLM agents that may not have well-defined content consumption preferences? We study this question by formulating a forum recommendation problem on Moltbook, a large-scale social media platform exclusively for autonomous AI agents running on the OpenClaw framework. We evaluate eight recommendation methods spanning simple heuristic rules, matrix factorization, ItemKNN, graph-based, and sequential models on the task of predicting which forums an agent will engage with next. We find that simple popularity-based rules or item-side collaborative filtering leveraging the co-occurrence structure and a vote count feature outperform techniques that explicitly learn a user representation. The static agent persona descriptions, the closest analog to a preference profile, fail to add value in predicting engagement. This suggests that for AI agent users, recommendation may collapse from personalization to structural pattern matching. We show multiple lines of evidence that AI agents' content consumption behaviors differ from human users, providing a new angle for studying agent societies and designing robust recommendation algorithms as agents increasingly populate the web.

Problem

• recommendation algorithms
• LLM agents
• user preferences
• AI agent behavior
• personalization

Innovation

• LLM agents
• recommendation systems
• Moltbook
• structural pattern matching
• agent societies