Personalized Communication Skills for Agentic Recommender Systems

2026-08-08

AI Summary

This work addresses the narrow perspective and resultant preference bias in existing large language model–driven user agents, which stem from their reliance on limited historical data. To overcome this limitation, the authors propose AgentCom, a novel framework that, for the first time, models personalized communication skills as a structured why–what–how–who skill repository. AgentCom introduces personalized skill routing and a failure-driven skill evolution mechanism, enabling multiple agents to dynamically invoke and continuously refine communication strategies based on the user’s decision state. Experimental results demonstrate that this approach significantly enhances recommendation performance across traditional, social, and agent-based recommender systems, effectively mitigating the narrow-perspective problem and underscoring the critical role of structured, evolvable communication mechanisms in personalized recommendation.

Abstract

Agentic recommender systems increasingly employ large language model-based UserAgents to evaluate candidate items through simulated feedback before recommendations are delivered. However, existing UserAgents typically reason in isolation based on limited personal histories, which may lead to perspective narrowing: the agent evaluates candidates from a local and incomplete view, overlooks relevant preference facets, and consequently produces inaccurate judgments. A natural way to alleviate this problem is to introduce other users as advisor agents, whose diverse histories provide complementary evidence that helps the target user reconsider overlooked preference signals. Nevertheless, a generic user-advisor communication process is insufficient, as different user decision states require different forms of external advice. Based on this insight, we propose AgentCom, a personalized communication skill framework for agentic recommender systems. AgentCom organizes reusable communication skills into a shared why--what--how--who skill bank: why identifies the decision deficiency that necessitates communication, what specifies the information task, how determines the advisor interaction protocol, and who retrieves advisors capable of executing that protocol. To make the shared skill bank personalized at use time and adaptive over time, AgentCom introduces two complementary mechanisms: personalized skill routing and failure-driven skill evolution. Personalized skill routing constructs a communication path by sequentially selecting suitable skills for each user and recommendation context. Failure-driven skill evolution learns from unsuccessful communication cases and enriches the shared bank with reusable skills that address previously uncovered communication needs. Experiments show that AgentCom consistently improves recommendation performance across traditional, social, and agentic recommenders.

Problem

• perspective narrowing
• agentic recommender systems
• personalized communication
• user decision states
• advisor agents

Innovation

• personalized communication
• agentic recommender systems
• skill bank
• skill routing
• failure-driven evolution