VRAgent-R1: Boosting Video Recommendation with MLLM-based Agents via Reinforcement Learning
July 03, 2025 Β· Declared Dead Β· π arXiv.org
"No code URL or promise found in abstract"
Evidence collected by the PWNC Scanner
Authors
Siran Chen, Boyu Chen, Chenyun Yu, Yuxiao Luo, Ouyang Yi, Lei Cheng, Chengxiang Zhuo, Zang Li, Yali Wang
arXiv ID
2507.02626
Category
cs.MM: Multimedia
Citations
6
Venue
arXiv.org
Last Checked
3 months ago
Abstract
Owing to powerful natural language processing and generative capabilities, large language model (LLM) agents have emerged as a promising solution for enhancing recommendation systems via user simulation. However, in the realm of video recommendation, existing studies predominantly resort to prompt-based simulation using frozen LLMs and encounter the intricate challenge of multimodal content understanding. This frequently results in suboptimal item modeling and user preference learning, thereby ultimately constraining recommendation performance. To address these challenges, we introduce VRAgent-R1, a novel agent-based paradigm that incorporates human-like intelligence in user simulation. Specifically, VRAgent-R1 comprises two distinct agents: the Item Perception (IP) Agent and the User Simulation (US) Agent, designed for interactive user-item modeling. Firstly, the IP Agent emulates human-like progressive thinking based on MLLMs, effectively capturing hidden recommendation semantics in videos. With a more comprehensive multimodal content understanding provided by the IP Agent, the video recommendation system is equipped to provide higher-quality candidate items. Subsequently, the US Agent refines the recommended video sets based on in-depth chain-of-thought (CoT) reasoning and achieves better alignment with real user preferences through reinforcement learning. Experimental results on a large-scale video recommendation benchmark have demonstrated the effectiveness of our proposed VRAgent-R1 method, e.g., the IP Agent achieves a 6.0\% improvement in NDCG@10 on the MicroLens-100k dataset, while the US Agent shows approximately 45.0\% higher accuracy in user decision simulation compared to state-of-the-art baselines.
Community Contributions
Found the code? Know the venue? Think something is wrong? Let us know!
π Similar Papers
In the same crypt β Multimedia
π
π
Old Age
R.I.P.
π»
Ghosted
Viewport-Adaptive Navigable 360-Degree Video Delivery
π
π
The Cartographer
A Comprehensive Survey on Cross-modal Retrieval
π
π
The Cartographer
An Overview of Cross-media Retrieval: Concepts, Methodologies, Benchmarks and Challenges
R.I.P.
π»
Ghosted
A Convolutional Neural Network Approach for Post-Processing in HEVC Intra Coding
R.I.P.
π»
Ghosted
Video Generation From Text
Died the same way β π» Ghosted
R.I.P.
π»
Ghosted
Federated Learning: Strategies for Improving Communication Efficiency
R.I.P.
π»
Ghosted
In-Datacenter Performance Analysis of a Tensor Processing Unit
R.I.P.
π»
Ghosted
Deep Convolutional Neural Networks for Computer-Aided Detection: CNN Architectures, Dataset Characteristics and Transfer Learning
R.I.P.
π»
Ghosted