AdaptJobRec: Enhancing Conversational Career Recommendation through an LLM-Powered Agentic System

TL;DR

AdaptJobRec tackles the latency bottleneck in agentic conversational job recommendation by introducing a complexity identification mechanism that routes simple queries to fast tools while complex queries engage memory processing and a planning module. The system leverages the Walmart People.AI knowledge graph to power personalized recommendation tools, enabling asynchronous sub-task execution and more accurate recommendations. Evaluations on Walmart real-world data show up to 53% reduction in response latency and improvements in recommendation accuracy and career-path prediction. The work demonstrates a practical, scalable architecture for latency-aware agentic CRS with potential for deployment in large-scale enterprise settings.

Abstract

In recent years, recommendation systems have evolved from providing a single list of recommendations to offering a comprehensive suite of topic focused services. To better accomplish this task, conversational recommendation systems (CRS) have progressed from basic retrieval augmented LLM generation to agentic systems with advanced reasoning and self correction capabilities. However, agentic systems come with notable response latency, a longstanding challenge for conversational recommendation systems. To balance the trade off between handling complex queries and minimizing latency, we propose AdaptJobRec, the first conversational job recommendation system that leverages autonomous agent to integrate personalized recommendation algorithm tools. The system employs a user query complexity identification mechanism to minimize response latency. For straightforward queries, the agent directly selects the appropriate tool for rapid responses. For complex queries, the agent uses the memory processing module to filter chat history for relevant content, then passes the results to the intelligent task decomposition planner, and finally executes the tasks using personalized recommendation tools. Evaluation on Walmart's real world career recommendation scenarios demonstrates that AdaptJobRec reduces average response latency by up to 53.3% compared to competitive baselines, while significantly improving recommendation accuracy.

Figures (5)

• Figure 1: Architecture of AdaptJobRec Agentic System
• Figure 2: System Prompt of Complexity Identification Mechanism.
• Figure 3: System Prompt of Few-shot Learning Memory Processing Module.
• Figure 4: System Prompt of AdaptJobRec Planner.
• Figure 5: AdaptJobRec Agentic System Deployment Architecture