7 papers
AUSO: Action-Level Unified Skill Optimization from Internalization to Utilization
Huizu Lin, Chengkai Huang, Tianqi Gao +5
Skills play different roles as an agent's policy evolves: they should first provide learnable knowledge, then support capability formation, and finally be invoked only when they im…
Beyond Item Order: Temporal Gap Tokenization for Generative Recommendation with Semantic IDs
Chengkai Huang, Tianqi Gao, Hongtao Huang +2
Semantic-ID-based generative recommendation has recently emerged as a scalable paradigm for sequential recommendation, where each item is represented by a compact sequence of discr…
Factorized Latent Reasoning for LLM-based Recommendation
Tianqi Gao, Chengkai Huang, Zihan Wang +3
Large language models (LLMs) have recently been adopted for recommendation by framing user preference modeling as a language generation problem. However, existing latent reasoning…
Getting Better at Working With You: Compiling User Corrections into Runtime Enforcement for Coding Agents
Yujun Zhou, Kehan Guo, Haomin Zhuang +8
Interactive LLM agents are becoming part of daily work, but they do not reliably become easier to work with over time: a correction remembered in one session may still be violated…
Alignment Risks from Capability-Seeking RL Training
Yujun Zhou, Yue Huang, Han Bao +8
While most AI alignment research focuses on preventing models from generating explicitly harmful content, a more subtle risk arises from capability-seeking RL training in vulnerabl…
Reflections and New Directions for Human-Centered Large Language Models
Caleb Ziems, Dora Zhao, Rose E. Wang +55
Large Language Models (LLMs) are increasingly shaping the private and professional lives of users, with numerous applications in business, education, finance, healthcare, law, and…