Agent4Rec
Overview
An open-source recommender system simulator utilizing 1,000 LLM-empowered generative agents to emulate user interactions with personalized movie recommendations.
Agent4Rec is an innovative recommender system simulator that leverages Large Language Models (LLMs) to create 1,000 generative agents, each initialized from the MovieLens-1M dataset. These agents exhibit diverse social traits and preferences, engaging in realistic interactions with personalized movie recommendations. Actions include watching, rating, evaluating, exiting, and conducting interviews about recommended content. Designed to provide insights into human behavior within recommendation environments, Agent4Rec serves as a valuable tool for researchers and developers aiming to study and enhance recommender systems.
AI Agent Store research
What the evidence says about Agent4Rec
Agent4Rec is research code for simulating recommender-system users with LLM-powered generative agents, not a consumer recommendation agent or hosted service. It models user profiles, memories, and actions so researchers can study how simulated users respond to personalized movie recommendations.
Last reviewed August 9, 2026
Verified capabilities
- LLM user simulation
Generative agents combine profile, factual and emotional memory, reflection, and action modules to simulate interactions with recommender systems.[2]
- Recommendation experiments
The code supports multiple recommendation baselines and configurable numbers of avatars, pages, items, and parallel execution settings.[1]
- Recorded simulation outputs
Interaction histories and experiment results are written to local storage for subsequent analysis.[1]
Where it fits best
Important considerations
- The authors report both alignment and deviation between simulated agents and real user preferences, so synthetic behavior should not be treated as a faithful substitute for human evaluation.[2]
- The repository was tested on Python 3.9.12 and warns that Python versions above 3.10 may trigger dependency bugs; running simulations also requires an external model API key.[1]
Sources and research method (2)
We record only claims tied to public sources checked by our team or listing workflow. Counts above are derived directly from this profile, not a subjective rating.
- LehengTHU/Agent4RecGitHub · checked 2026-08-09
- On Generative Agents in RecommendationDocumentation · checked 2026-08-09
Autonomy level
72%
Comparisons
Custom Comparisons
Some of the use cases of Agent4Rec:
- Simulating user interactions to study behavior in recommendation systems.
- Testing and refining recommendation algorithms with realistic user simulations.
- Analyzing the impact of diverse user preferences on recommender performance.
- Exploring phenomena such as the filter bubble effect in recommendation environments.
- Conducting large-scale simulations without the need for real user studies.
Loading Community Opinions...
Pricing model:
Code access:
Popularity level: 57%
Industries:
Tags:
Turn this profile into a trust signal
Show prospects that Agent4Rec has a public place where they can check product details, pricing, ratings, and reviews.
Build confidence
Give buyers a third-party profile to explore.
Reduce hesitation
Put validation beside your strongest CTA.
Earn discovery
Every badge links prospects to your listing.
Choose your style
Preview it, then copy the complete embed code.
Shows buyers where to validate your product, pricing, and reputation.
Plain HTML. No signup, script, or maintenance required.
Describe the job. Get an AI worker you can actually message.
We create the setup, keep it running after your laptop closes, and save its memory. Test in the browser, then add Telegram, WhatsApp, or Slack.
Plans start at $29/month. Cancel anytime.
Hosted agent
OpenClaw or Hermes