Reproduce “Prospect Personalized Recommendation on Large Language Model-based Agent Platform” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Jizhi Zhang, Keqin Bao, Wenjie Wang, Yang Zhang, Wentao Shi, Wanhong Xu, Fuli Feng, Tat-Seng Chua
This research introduces "Rec4Agentverse," a new recommendation paradigm treating Large Language Model (LLM)-based Agents as the items to be recommended. The framework outlines how users, intelligent agents, and a central recommender can engage in evolving collaborative stages to deliver dynamic, deeply personalized services.
Key insights
- LLM-based Agents can function as interactive, intelligent, and proactive "Agent Items," fundamentally altering the nature of recommendable entities.
- The paradigm enables a multi-directional information flow, encompassing direct user-agent dialogue, bidirectional agent-recommender exchange, and collaborative interactions among agents.
- Rec4Agentverse offers a path toward dynamic, deeply personalized services where agents continuously learn user preferences and adapt their capabilities through ongoing interactions.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.