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

2025-08-18

AI Summary

Addressing the inherent trade-off between handling complex queries and achieving low-latency responses in conversational career recommendation, this paper proposes a large language model–based adaptive agent system. The method introduces a novel query complexity identification mechanism that dynamically selects between direct tool invocation and deep reasoning pathways, integrated with memory management, task decomposition planning, and personalized recommendation modules. Unlike static pipeline designs, our approach is the first to jointly optimize reasoning depth and response efficiency specifically for career recommendation. Evaluated on Walmart’s real-world production environment, the system achieves up to a 53.3% reduction in average response latency and a 12.7% improvement in Top-3 recommendation accuracy over baseline models, demonstrating significant gains in both real-time responsiveness and recommendation quality.

Technology Category

• Data Mining & Knowledge Management: Conversational Systems for Recommendation & Retrieval
• Planning, Routing, and Scheduling: Planning with Language Models
• Multiagent Systems: Agent Communication

Application Category

• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation
• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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.

Problem

• Reducing response latency in conversational job recommendation systems
• Balancing complex query handling with minimized system latency
• Integrating personalized algorithms into autonomous agentic recommendation systems

Innovation

• Agentic system with autonomous tool integration
• Query complexity identification for latency reduction
• Memory processing and task decomposition planner