Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations
Open accessAbstract
Recommender models capture ever-changing user preferences by training with in-domain user behavior data. These models are typically lightweight, facilitating real-time and large-scale online services. However, these models often falter when tasked with providing more sophisticated functionalities, such as offering explanations or engaging in conversations. Recently, large language models (LLMs) have emerged as a significant advancement towards artificial general intelligence, demonstrating impressive capabilities in instruction comprehension, reasoning, and human interaction. Unfortunately, LLMs lack the understanding of domain-specific item catalogs and behavioral patterns, especially in areas that deviate from general world knowledge, such as online e-commerce. This limitation makes them unsuitable to function as recommender models directly. In this article, we bridge the gap between recommender models and LLMs, combining their respective strengths to create an interactive recommender system. We present an efficient framework, termed as InteRecAgent , which utilizes LLMs as the brain and recommender models as instrumental tools. We first outline a minimal set of essential tools required to transform LLMs into InteRecAgent. To overcome specific challenges associated with LLM-based agents for recommender systems, we enhance three core components, covering memory mechanism, task planning, and tool learning abilities. The InteRecAgent empowers traditional recommender systems, like ID-based matrix factorization models, to evolve into versatile and interactive systems with a natural language interface through the integration of LLMs. Experimental results derived from three public datasets demonstrate that the InteRecAgent delivers strong performance as a conversational recommender system, surpassing general LLMs such as GPT-4.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The final generated Z vector serves as attention-weighted control for downstream user memory retrieval modules, improving the sensitivity and generalization capability of personalized semantic retrieval.
“The final generated 𝑍 vector serves as attentionweighted control for downstream user memory retrieval modules, thereby improving the sensitivity and generalization capability of personalized semantic retrieval4 , as shown in Figure 2.”
From Enhancing Search Efficiency through LLM-Based User Memory Systems for Query Matching and Intent Modeling (2026) · cites this paper as [4]
Agentic AI is built strongly on top of LLMs and RL.
“Agentic AI is built strongly on top of LLMs and RL.”
From The Rise of Agentic AI: A Review of Definitions, Frameworks, Architectures, Applications, Evaluation Metrics, and Challenges (2025) · cites this paper as [79]
Interactive recommender systems will provide conversational personalized recommendations across movies/entertainment and retail domains.
“Interactive recommender systems will provide conversational personalized recommendations across movies/entertainment and retail domains [79].”
From The Rise of Agentic AI: A Review of Definitions, Frameworks, Architectures, Applications, Evaluation Metrics, and Challenges (2025) · cites this paper as [79]
Agentic AI models have maintained high recall across different applications like EcoptiAI in e-commerce retrieval, LLaMA 3.1 in clinical text extraction, InteRecAgent potentially using RecLLaMA in recommendation systems, and GPT-4o in digital twins in fault detection.
“Agentic AI models have maintained high recall across different applications like EcoptiAI [142] in e-commerce retrieval, LLaMA 3.1 [102] in clinical text extraction, InteRecAgent potentially using RecLLaMA [79] in recommendation systems, and GPT-4o [126] in digital twins in fault detection.”
From The Rise of Agentic AI: A Review of Definitions, Frameworks, Architectures, Applications, Evaluation Metrics, and Challenges (2025) · cites this paper as [79]
Multi-agent cross-verification, confidence-based reruns, and actor-critic feedback loops improve reliability in dynamic scenarios.
“Multi-agent cross-verification, confidence-based reruns, and actorcritic feedback loops improve reliability in dynamic scenarios [65,79,140].”
From The Rise of Agentic AI: A Review of Definitions, Frameworks, Architectures, Applications, Evaluation Metrics, and Challenges (2025) · cites this paper as [79]
Cites
Training language models to follow instructions with human feedback
Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C. L., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., et al. (2022) · arXiv · doi:10.48550/arxiv.2203.02155 · Cited by 4,208 · see citing works
A survey on large language model based autonomous agents
Wang, L., Ma, C., Feng, X., Zhang, Z., Yang, H., Zhang, J., Chen, Z., Tang, J., Chen, X., Lin, Y., et al. (2024) · Frontiers of Computer Science · doi:10.1007/s11704-024-40231-1 · Cited by 1,941 · see citing works
Learning To Retrieve Prompts for In-Context Learning
Rubin, O., Herzig, J., & Berant, J. (2022) · Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies · doi:10.18653/v1/2022.naacl-main.191 · Cited by 374 · see citing works
Plan-and-Solve Prompting: Improving Zero-Shot Chain-of-Thought Reasoning by Large Language Models
Wang, L., Xu, W., Lan, Y., Hu, Z., Lan, Y., Lee, R. K.-W., & Lim, E.-P. (2023) · Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers) · doi:10.18653/v1/2023.acl-long.147 · Cited by 344 · see citing works
Towards Unified Conversational Recommender Systems via Knowledge-Enhanced Prompt Learning
Wang, X., Zhou, K., Wen, J.-R., & Zhao, W. X. (2022) · Proceedings of the 28th ACM SIGKDD Conference on Knowledge Discovery and Data Mining · doi:10.1145/3534678.3539382 · Cited by 164 · see citing works
Flagged first, then by citations
Cited by
Sorted by citations
Recommender Systems in the Era of Large Language Models (LLMs)
Zhao, Z., Fan, W., Li, J., Liu, Y., Mei, X., Wang, Y., Wen, Z., Wang, F., Zhao, X., Tang, J., et al. (2024) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2024.3392335 · Cited by 481 · see citing works
Bandi, A., Kongari, B., Naguru, R., Pasnoor, S., & Vilipala, S. V. (2025) · Future Internet · doi:10.3390/fi17090404 · Cited by 207 · see citing works
A foundational architecture for AI agents in healthcare
Liu, F., Niu, Y., Zhang, Q., Wang, K., Dong, Z., Wong, I. N., Cheng, L., Li, T., Duan, L., Li, K., et al. (2025) · Cell Reports Medicine · doi:10.1016/j.xcrm.2025.102374 · Cited by 41 · see citing works
From language to action: a review of large language models as autonomous agents and tool users
Chowa, S. S., Alvi, R., Rahman, S. S., Rahman, M. A., Raiaan, M. A. K., Islam, M. R., Hussain, M., & Azam, S. (2026) · Artificial Intelligence Review · doi:10.1007/s10462-025-11471-9 · Cited by 50 · see citing works
“Agents simulate realistic user behavior for testing [102] and provide interactive recommendation dialogues [84], capturing evolving user intent with minimal supervision.”
InfluentialBalaskas, S. (2026) · Information · doi:10.3390/info17030222 · Cited by 8 · see citing works
Explaining Length Bias in LLM-Based Preference Evaluations
Hu, Z., Song, L., Zhang, J., Xiao, Z., Wang, T., Chen, Z., Yuan, N. J., Lian, J., Ding, K., & Xiong, H. (2025) · Findings of the Association for Computational Linguistics: EMNLP 2025 · doi:10.18653/v1/2025.findings-emnlp.358 · Cited by 4 · see citing works
“LLM-based auto-evaluators have emerged as a crucial tool in this context, offering a cost-effective and scalable alternative to labor-intensive human evaluations (Li et al., 2024a,b; Dubois et al., 2024b; Huang et al., 2025; Song et al., 2024a; Zhan et al., 2025).”
Self-citationFrom Human Memory to AI Memory: A Survey on Memory Mechanisms in the Era of LLMs
Wu, Y., Liang, S., Zhang, C., Wang, Y., Zhang, Y., Guo, H., Tang, R., & Liu, Y. (2025) · arXiv · doi:10.48550/arxiv.2504.15965 · Cited by 3 · see citing works
“…Human-like Memory [60], HippoRAG [13], HippoRAG 2 [61], EgoRAG [62], MemInsight [50] Usage MemoCRS [63], RecMind [64], RecAgent [65], InteRecAgent [66], SCM [67], ChatDev [68], MetaAgents [69], S 3 [70], TradingGPT [71], Memolet [72], Synaptic Resonance [14], MemReasoner [73] Benchmark…”
A Survey of Agent Memory in the Second Half: Towards Self-Evolving and Long-Horizon Agents
Huang, W.-C., Zhang, W., Liang, Y., Bei, Y., Chen, Y., Feng, T., Pan, X., Tan, Z., Wang, Y., Wei, T., et al. (2026) · arXiv · doi:10.48550/arxiv.2602.06052
- Authors
- Huang, X., Lian, J., Lei, Y., Yao, J., Lian, D., & Xie, X.
- Affiliations
- University of Science and Technology of China (CN)
- Microsoft Research Asia (China) (CN)
- Venue
- ACM Transactions on Information Systems
- Published
- 2025-06-16
- Volume
- 43
- Issue
- 4
- Pages
- 1-33
- ISSN
- 1046-8188 (ISSN-L)
- 1558-2868
- OpenAlex
- W4409643680
- Cited by
- 89
- References
- 5
- Citations by year
- 2026: 50 · 2025: 34 · 2024: 4 · 2023: 1
- FWCI
- 87.34
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Locations
- ACM Transactions on Information Systems (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Information Systems › Recommender Systems and Techniques
- Physical Sciences › Computer Science › Information Systems › Information Retrieval and Search Behavior
- Physical Sciences › Computer Science › Artificial Intelligence › AI in Service Interactions
- Keywords
- conversational recommender systems, large language models, recommendation agents, interactive recommendation, LLM agents, memory mechanisms, task planning, tool learning, natural language interfaces, e-commerce recommendation, matrix factorization
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
