Personalized Recommendation Tool Learning via Autonomous Language Agents
Open Access
- 27 September 2026
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 722-727
Abstract
Although large language models (LLMs) have recently gained traction in recommender systems due to their strong reasoning capabilities and extensive world knowledge, previous LLM-based agents suffer from hallucination and context-length limitations, and thus are not suitable for full-ranking recommendation tasks. To circumvent these limitations through architectural design rather than modifying the LLM itself, we propose an agent-based recommendation framework, memory-based Personalized Recommendation Tool learning via autonomous language Agents (PRTA), in which an LLM acts as a central planner interacting with multiple recommendation models as tools. The LLM-based agent is responsible for high-level reasoning and personalized tool selection, while traditional recommendation models perform full-ranking scoring, leveraging their scalability in modeling behavioral patterns. To support personalized tool selection, we design reflection mechanisms that enable the agent to evaluate and compare tools for each user based on user profiles and candidate ranked lists. Extensive experiments across three public datasets demonstrate the superiority of PRTA over traditional recommendation and LLM-based baselines in improving full-ranking recommendation performance. Our code implementation is available online1.Keywords
All Related Versions
Funding Information
- NSFC (U25B2029)
- NSFC (62322202)
- Beijing Natural Science Foundation (L253021)
- Science Research Project of Hebei Higher Education Institutions (CYZD2026005)
- Major Science and Technology Special Projects of Yunnan Province (202502AD080012)
- Major Science and Technology Special Projects of Yunnan Province (202502AD080006)
This publication has 30 references indexed in Scilit:
- Large Language Models are Zero-Shot Rankers for Recommender Systems2024
- Diffusion Recommender Model2023
- Frequency Enhanced Hybrid Attention Network for Sequential Recommendation2023
- Survey of Hallucination in Natural Language GenerationACM Computing Surveys, 2023
- Recommendation as Language Processing (RLP): A Unified Pretrain, Personalized Prompt & Predict Paradigm (P5)2022
- SimpleX2021
- RecBole: Towards a Unified, Comprehensive and Efficient Framework for Recommendation Algorithms2021
- LightGCN2020
- Efficient Neural Matrix Factorization without Sampling for RecommendationACM Transactions on Information Systems, 2020
- Self-Attentive Sequential Recommendation2018