AgenticRAG: Tool-Augmented Foundation Models for Zero-Shot Explainable Recommender Systems

2025/10/03 by Bo Ma, Hang Li, Ma, Bo +8
Computer Science · #Artificial Intelligence (cs.AI) #Explainable Artificial Intelligence (XAI) #FOS: Computer and information sciences #Information Retrieval (cs.IR) #Multimodal Machine Learning Applications #Recommender Systems and Techniques

paper · pdf · doi:10.48550/arxiv.2510.02668

openalex publication_date 2025/10/03 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Foundation models have revolutionized artificial intelligence, yet their application in recommender systems remains limited by reasoning opacity and knowledge constraints. This paper introduces AgenticRAG, a novel framework that combines tool-augmented foundation models with retrieval-augmented generation for zero-shot explainable recommendations. Our approach integrates external tool invocation, knowledge retrieval, and chain-of-thought reasoning to create autonomous recommendation agents capable of transparent decision-making without task-specific training. Experimental results on three real-world datasets demonstrate that AgenticRAG achieves consistent improvements over state-of-the-art baselines, with NDCG@10 improvements of 0.4% on Amazon Electronics, 0.8% on MovieLens-1M, and 1.6% on Yelp datasets. The framework exhibits superior explainability while maintaining computational efficiency comparable to traditional methods.

Citations

• AgentCF: Collaborative Learning with Autonomous Language Agents for Recommender Systems
• The Rise and Potential of Large Language Model Based Agents: A Survey
• Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations
• ReLLa: Retrieval-enhanced Large Language Models for Lifelong Sequential Behavior Comprehension in Recommendation
• AgentBench: Evaluating LLMs as Agents
• Lost in the Middle: How Language Models Use Long Contexts
• A Survey on Large Language Models for Recommendation
• Large Language Models are Zero-Shot Rankers for Recommender Systems
• MiniGPT-4: Enhancing Vision-Language Understanding with Advanced Large Language Models
• Is ChatGPT Good at Search? Investigating Large Language Models as Re-Ranking Agents
• Tool Learning with Foundation Models
• Generative Agents: Interactive Simulacra of Human Behavior
• A Survey of Large Language Models
• Chat-REC: Towards Interactive and Explainable LLMs-Augmented Recommender System
• Sparks of Artificial General Intelligence: Early experiments with GPT-4
• GPT-4 Technical Report
• Visual ChatGPT: Talking, Drawing and Editing with Visual Foundation Models
• PaLM-E: An Embodied Multimodal Language Model
• LLaMA: Open and Efficient Foundation Language Models
• AugGPT: Leveraging ChatGPT for Text Data Augmentation
• Augmented Language Models: a Survey
• Toolformer: Language Models Can Teach Themselves to Use Tools
• Self-Instruct: Aligning Language Models with Self-Generated Instructions
• Affective Coherence Monitoring for Transformer-Based Language Models
• Learning Vector-Quantized Item Representation for Transferable Sequential Recommenders
• ReAct: Synergizing Reasoning and Acting in Language Models
• Improving alignment of dialogue agents via targeted human judgements
• Code as Policies: Language Model Programs for Embodied Control
• OPT: Open Pre-trained Transformer Language Models
• PaLM: Scaling Language Modeling with Pathways
• Training Compute-Optimal Large Language Models
• CodeGen: An Open Large Language Model for Code with Multi-Turn Program Synthesis
• Training language models to follow instructions with human feedback
• BNAI, NO-TOKEN, and MIND-UNITY: Pillars of a Systemic Revolution in Artificial Intelligence
• LaMDA: Language Models for Dialog Applications
• WebGPT: Browser-assisted question-answering with human feedback
• A General Language Assistant as a Laboratory for Alignment
• On the Opportunities and Risks of Foundation Models
• Evaluating Large Language Models Trained on Code
• GLM: General Language Model Pretraining with Autoregressive Blank Infilling
• Language Models are Few-Shot Learners
• Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks
• Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer
• Self-Attentive Sequential Recommendation
• Neural Collaborative Filtering
• Session-based Recommendations with Recurrent Neural Networks
• Image-based Recommendations on Styles and Substitutes
• BPR: Bayesian Personalized Ranking from Implicit Feedback
• User Behavior Simulation with Large Language Model based Agents
• HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
• BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding

Related

• STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning
• A Survey of Foundation Model-Powered Recommender Systems: From Feature-Based, Generative to Agentic Paradigms
• ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation
• Towards Agentic Recommender Systems in the Era of Multimodal Large Language Models
• The Future is Agentic: Definitions, Perspectives, and Open Challenges of Multi-Agent Recommender Systems