Agent web improves personalized recommendations by fusing user data
AgentWebRec: Compact Evidence Fusion over the Agent Web for Personalized Recommendation
Information Retrieval
Summary
Traditional recommendation systems mainly use data collected by platforms, which can miss rich personal preferences. The authors present AgentWebRec, a system where personal AI agents keep user preferences locally and communicate with each other to share useful information. This creates a network of agents that helps the platform give better recommendations by smartly asking and combining relevant user data from connected agents without sharing everything. Tests on multiple datasets showed this approach consistently works better than typical recommenders.
What this means in practice
- •For e-commerce platform teams: Enhance product recommendations by integrating distributed personal agent data without exposing full user histories.$Commercial implications: Enables building privacy-preserving recommendation features that use richer user preferences from interconnected personal agents.
- •For mobile app developers: Develop apps that improve user suggestions by querying agent networks to gather and combine relevant preferences dynamically.
Authors
Haoran Qiang, Guannan Liu, Liang Zhang, Junjie Wu
Abstract
LLM-based personal agents are emerging as persistent carriers of user semantics and intermediaries between users and recommendation platforms, maintaining richer user knowledge locally. As agents interact with one another, the conventional \textit{User--Platform} relation evolves into a \textit{User--Agent Web--Platform} information pathway, enabling distributed user-side information to complement item-side information. This new pathway, however, defies conventional recommendation: evidence is scattered across mutually opaque agents and reachable only through bounded queries, only a small portion of it is relevant to the current recommendation decision, and the responses returned by different agents are semantically heterogeneous. We therefore recast recommendation over the agent web as a \emph{task-time evidence acquisition and fusion} problem under a finite evidence budget by deciding what to ask and what to keep, rather than learning from aggregated data. We propose AgentWebRec, a user-agent-oriented framework that progressively acquires and fuses distributed evidence for each user-item decision while keeping underlying agent memories local. It grounds each decision in platform-provided item semantics and task-relevant evidence from the target user agent's private memory, and conditionally queries neighboring user agents for complementary preference patterns when local evidence is insufficient. Experiments on four InstructRec datasets show that AgentWebRec consistently outperforms baseline recommenders, and ablations verify that the evidence layers contribute complementary gains.