AgenticRS-Architecture: System Design for Agentic Recommender Systems
Hao Zhang, Jinxin Hu, Hao Deng, Lingyu Mu, Shizhun Wang, Yu Zhang, Xiaoyi Zeng

TL;DR
AutoModel is an agent-based architecture that automates the full lifecycle of industrial recommender systems through interconnected agents with self-improvement capabilities.
Contribution
It introduces a novel agent-based system design for recommender systems, enabling automated, scalable, and adaptive model development and deployment.
Findings
AutoTrain automates paper-driven model reproduction, reducing manual effort.
AutoModel enables localized yet globally coordinated evolution of recommender systems.
The architecture can be generalized to other AI systems like search and advertising.
Abstract
AutoModel is an agent based architecture for the full lifecycle of industrial recommender systems. Instead of a fixed recall and ranking pipeline, AutoModel organizes recommendation as a set of interacting evolution agents with long term memory and self improvement capability. We instantiate three core agents along the axes of models, features, and resources: AutoTrain for model design and training, AutoFeature for data analysis and feature evolution, and AutoPerf for performance, deployment, and online experimentation. A shared coordination and knowledge layer connects these agents and records decisions, configurations, and outcomes. Through a case study of a module called paper autotrain, we show how AutoTrain automates paper driven model reproduction by closing the loop from method parsing to code generation, large scale training, and offline comparison, reducing manual effort for…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
