8 papers
LeanMem: Simple and Efficient Long-Term Memory for LLM Agents
Yuxin Liao, Le Wu, Min Hou +3
Long-term memory is essential for LLM-based agents to sustain interactions and reliably leverage distant history. However, existing memory systems typically process heterogeneous d…
VC-Soup: Value-Consistency Guided Multi-Value Alignment for Large Language Models
Hefei Xu, Le Wu, Yu Wang +4
As large language models (LLMs) increasingly shape content generation, interaction, and decision-making across the Web, aligning them with human values has become a central objecti…
A Survey on Generative Recommendation: Data, Model, and Tasks
Min Hou, Le Wu, Yuxin Liao +6
Recommender systems serve as foundational infrastructure in modern information ecosystems, helping users navigate digital content and discover items aligned with their preferences.…
MLLMRec-R1: Incentivizing Reasoning Capability in Large Language Models for Multimodal Sequential Recommendation
Yu Wang, Yonghui Yang, Le Wu +3
Group relative policy optimization (GRPO) has become a standard post-training paradigm for improving reasoning and preference alignment in large language models (LLMs), and has rec…
From Atom to Community: Structured and Evolving Agent Memory for User Behavior Modeling
Yuxin Liao, Le Wu, Min Hou +3
User behavior modeling lies at the heart of personalized applications like recommender systems. With LLM-based agents, user preference representation has evolved from latent embedd…
An Efficient LLM-based Evolutional Recommendation with Locate-Forget-Update Paradigm
Hao Liu, Le Wu, Min Hou +4
Nowadays, Large Language Models (LLMs) have shown exceptional performance in sequential recommendations, and the adoption of LLM-based recommender systems (LLMRec) is becoming incr…