Skip to content
Preprint

Agents as Knowledge Integrator and Utilizer in Multimodal Recommendation

Aug 2026 · 0 citations · 42 references
Computer Science

TL;DR

This work proposes AgentMMRec, an agent-based multimodal recommendation framework with two coordinated roles that consistently improves Recall and NDCG over recent multimodal baselines, remains effective under sparsity and item cold-start settings, and can transfer its constructed knowledge to existing backbones.

Abstract

Online platforms increasingly rely on multimodal recommender systems to rank products, media, and other Web content. Existing methods usually inject visual and textual features into item representations or build homogeneous graphs from modality-level similarity, but the resulting signals can remain misaligned with the recommendation objective. We study this semantic gap from a knowledge-integration perspective: multimodal content should be interpreted together with user behavior before it is used to construct recommendation graphs or adjust rankings. We propose AgentMMRec, an agent-based multimodal recommendation framework with two coordinated roles. The Integrator Agent infers behavior- and multimodal-aware user preferences and item properties from training interactions and item content, then stores them in a reusable knowledge memory. The Utilizer Agent consumes this memory to refine modality-specific item-item graphs, construct behavior-aware homogeneous graphs, and rerank candidate lists under a frozen evaluation-time memory. This design differs from direct LLM feature augmentation and pure LLM reranking because the generated knowledge is first converted into graph structure and model representations before recommendation. Experiments on three Amazon multimodal recommendation datasets show that AgentMMRec consistently improves Recall and NDCG over recent multimodal baselines, remains effective under sparsity and item cold-start settings, and can transfer its constructed knowledge to existing backbones.

View source

Similar papers

Review Open access Sep 2026

Hybrid Graph Retrieval-Augmented Language Agents for Collaborative Recommendation

Recent advances in large language model (LLM) agents have shown promise for autonomous decision-making in recommender systems. However, existing approaches suffer from two fundamental limitations: flat agent memories that conflate different information modalities and prohibitive computational costs that prevent scaling...

Ivan Bulychev, Andrey V. Savchenko · 0 citations
Preprint Oct 2026

Rethinking Evidence Modeling: Context-Coupled Graph Learning for Multimodal Recommendation

Multimodal graph recommendation integrates observed interactions with item images and text to learn user preferences. These inputs constitute Semantic-Behavioral Evidence (SBE). Many existing graph methods incorporate collaborative and multimodal semantic relations, yet their aggregation and state updates remain contex...

Ming-Qiao Zhang, Qi-Yao Peng, Yu-Meng Wang et al. · 0 citations
Preprint Sep 2026

AdaM-Rec: Adaptive Modality Routing for Multimodal Recommendation

While recent multimodal recommender systems have demonstrated the effectiveness of incorporating visual and textual information to improve downstream performance, most existing methods rely on static modality fusion, assuming that the relative importance of textual and visual signals remains stable across recommendatio...

Honghao Fu, Jiacheng Chen, Man-Xi Lin et al. · 0 citations
Preprint Oct 2026

AgentWebRec: Compact Evidence Fusion over the Agent Web for Personalized Recommendation

LLM-based personal agents are emerging as persistent carriers of user semantics and intermediaries between users and recommendation platforms, maintaining richer user knowledge locally. As agents interact with one another, the conventional \textit{User--Platform} relation evolves into a \textit{User--Agent Web--Platfor...

Hao-Ran Qiang, Guan-Nan Liu, Liang Zhang et al. · 0 citations

ReMem: Rethinking Perception and Memory in Long-Context Recommendation Agents

A novel recommendation agent framework, termed as ReMem, that combines OCR-based multimodal perception with time-evolving dynamic memory, which allows the agent to preserve evolving user preferences without relying on external memory modules or disrupting the standard autoregressive generation process.

Hao-Hao Qu, Yong-Cheng Jing, Chun-Hin Chan et al. · 0 citations

Mix-Attention for Multimodal Large Language Model-Enhanced Sequential Recommendation

Sequential recommendation aims to predict the next item that may interest users by modeling their historical item sequence. Recently, multimodal sequential recommendation has achieved promising results in capturing user preferences by incorporating rich modality information. However, existing frameworks suffer from lim...

Sheng-Hao Yang, Zhi-Qiang Guo, Wei-Zhi Ma et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.