# Towards Efficient Hypergraph and Multi-LLM Agent Recommender Systems

arXiv: https://arxiv.org/abs/2512.06590 · HTML: https://mlsanity.com/paper/2512.06590/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agentic recommender systems, one of 16 directions in LLM agents and tool use.
- Builds on 25 of its 37 references that are in the map.
- First posted on arXiv 6 Dec 2025.

## Placed in

- LLM agents and tool use / [Agentic recommender systems](https://mlsanity.com/agents/agentic-recommender-systems/)

## Builds on (most cited first, 25 of 25)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen2.5 Technical Report](https://mlsanity.com/paper/2412.15115/) (2024)
- [How Powerful are Graph Neural Networks?](https://mlsanity.com/paper/1810.00826/) (2018)
- [Tree of Thoughts: Deliberate Problem Solving with Large Language Models](https://mlsanity.com/paper/2305.10601/) (2023)
- [Self-Attentive Sequential Recommendation](https://mlsanity.com/paper/1808.09781/) (2018)
- [BERT4Rec: Sequential Recommendation with Bidirectional Encoder Representations from Transformer](https://mlsanity.com/paper/1904.06690/) (2019)
- [Mixture-of-Agents Enhances Large Language Model Capabilities](https://mlsanity.com/paper/2406.04692/) (2024)
- [Hypergraph Convolution and Hypergraph Attention](https://mlsanity.com/paper/1901.08150/) (2019)
- [Representation Learning with Large Language Models for Recommendation](https://mlsanity.com/paper/2310.15950/) (2023)
- [Recommender AI Agent: Integrating Large Language Models for Interactive Recommendations](https://mlsanity.com/paper/2308.16505/) (2023)
- [Let Your Graph Do the Talking: Encoding Structured Data for LLMs](https://mlsanity.com/paper/2402.05862/) (2024)
- [From Matching to Generation: A Survey on Generative Information Retrieval](https://mlsanity.com/paper/2404.14851/) (2024)
- [Test of Time: A Benchmark for Evaluating LLMs on Temporal Reasoning](https://mlsanity.com/paper/2406.09170/) (2024)
- [Leveraging Large Language Models for Sequential Recommendation](https://mlsanity.com/paper/2309.09261/) (2023)
- [Generative Recommendation: Towards Next-generation Recommender Paradigm](https://mlsanity.com/paper/2304.03516/) (2023)
- [GenRec: Large Language Model for Generative Recommendation](https://mlsanity.com/paper/2307.00457/) (2023)
- [Large Language Models for Next Point-of-Interest Recommendation](https://mlsanity.com/paper/2404.17591/) (2024)
- [Harnessing Large Language Models for Text-Rich Sequential Recommendation](https://mlsanity.com/paper/2403.13325/) (2024)
- [Large Language Model Augmented Narrative Driven Recommendations](https://mlsanity.com/paper/2306.02250/) (2023)
- [Graph Neural Networks with Adaptive Readouts](https://mlsanity.com/paper/2211.04952/) (2022)
- [Zero-Shot Recommendation as Language Modeling](https://mlsanity.com/paper/2112.04184/) (2021)
- [Personalized Behavior-Aware Transformer for Multi-Behavior Sequential Recommendation](https://mlsanity.com/paper/2402.14473/) (2024)
- [DynLLM: When Large Language Models Meet Dynamic Graph Recommendation](https://mlsanity.com/paper/2405.07580/) (2024)
- [Session-based Recommendation with Self-Attention Networks](https://mlsanity.com/paper/2102.01922/) (2021)
- [HMAR: Hierarchical Masked Attention for Multi-Behaviour Recommendation](https://mlsanity.com/paper/2405.09638/) (2024)

## Abstract (arXiv)

Recommender Systems (RSs) have become the cornerstone of various applications such as e-commerce and social media platforms. The evolution of RSs is paramount in the digital era, in which personalised user experience is tailored to the user's preferences. Large Language Models (LLMs) have sparked a new paradigm - generative retrieval and recommendation. Despite their potential, generative RS methods face issues such as hallucination, which degrades the recommendation performance, and high computational cost in practical scenarios. To address these issues, we introduce HGLMRec, a novel Multi-LLM agent-based RS that incorporates a hypergraph encoder designed to capture complex, multi-behaviour relationships between users and items. The HGLMRec model retrieves only the relevant tokens during inference, reducing computational overhead while enriching the retrieval context. Experimental results show performance improvement by HGLMRec against state-of-the-art baselines at lower computational cost.