Do Recommendation Algorithms Work When Users Are LLM Agents? A Case Study on Moltbook
2026-06-29 • Information Retrieval
Information Retrieval
AI summaryⓘ
The authors studied how recommendation algorithms work when the users are AI agents instead of humans. They tested different methods to predict which online forums AI agents would visit next on a platform called Moltbook. They found that simple popularity-based approaches worked better than complex methods that try to understand user preferences. This suggests that AI agents behave differently from humans, and recommendations for them may rely more on patterns than personalization. Their work highlights the need to rethink recommendation strategies as AI users become more common.
large language modelrecommendation systemMoltbookAI agentscollaborative filteringItemKNNuser representationpersonalizationcontent consumptionmatrix factorization
Authors
Daming Li, Simeng Han, Jialu Zhang
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.