5 papers
Code over Words: Overcoming Semantic Inertia via Code-Grounded Reasoning
Manjie Xu, Isabella Yin, Xinyi Tu +2
LLMs struggle with Semantic Inertia: the inability to inhibit pre-trained priors (e.g., "Lava is Dangerous") when dynamic, in-context rules contradict them. We probe this phenomeno…
HyMiRec: A Hybrid Multi-interest Learning Framework for LLM-based Sequential Recommendation
Jingyi Zhou, Cheng Chen, Kai Zuo +5
Large language models (LLMs) have recently demonstrated strong potential for sequential recommendation. However, current LLM-based approaches face critical limitations in modeling…
Cross-Scenario Unified Modeling of User Interests at Billion Scale
Manjie Xu, Cheng Chen, Xin Jia +9
User interests on content platforms are inherently diverse, manifesting through complex behavioral patterns across heterogeneous scenarios such as search, feed browsing, and conten…
Heterogeneous Adversarial Play in Interactive Environments
Manjie Xu, Xinyi Yang, Jiayu Zhan +3
Self-play constitutes a fundamental paradigm for autonomous skill acquisition, whereby agents iteratively enhance their capabilities through self-directed environmental exploration…
Learning to Plan with Personalized Preferences
Manjie Xu, Xinyi Yang, Wei Liang +2
Effective integration of AI agents into daily life requires them to understand and adapt to individual human preferences, particularly in collaborative roles. Although recent studi…