collaborators

7 papers

cs.LG2025

GeoGNN: Quantifying and Mitigating Semantic Drift in Text-Attributed Graphs

Liangwei Yang, Jing Ma, Jianguo Zhang +11

Graph neural networks (GNNs) on text--attributed graphs (TAGs) typically encode node texts using pretrained language models (PLMs) and propagate these embeddings through linear nei…

cs.LG2025

xRouter: Training Cost-Aware LLMs Orchestration System via Reinforcement Learning

Cheng Qian, Zuxin Liu, Shirley Kokane +10

Modern LLM deployments confront a widening cost-performance spectrum: premium models deliver strong reasoning but are expensive, while lightweight models are economical yet brittle…

cs.AI2025

UserRL: Training Interactive User-Centric Agent via Reinforcement Learning

Cheng Qian, Zuxin Liu, Akshara Prabhakar +10

Reinforcement learning (RL) has shown promise in training agentic models that move beyond static benchmarks to engage in dynamic, multi-turn interactions. Yet, the ultimate value o…

cs.AI2025

PersonaBench: Evaluating AI Models on Understanding Personal Information through Accessing (Synthetic) Private User Data

Juntao Tan, Liangwei Yang, Zuxin Liu +11

Personalization is critical in AI assistants, particularly in the context of private AI models that work with individual users. A key scenario in this domain involves enabling AI m…

cs.SE2025

ToolScan: A Benchmark for Characterizing Errors in Tool-Use LLMs

Shirley Kokane, Ming Zhu, Tulika Awalgaonkar +15

Evaluating Large Language Models (LLMs) is one of the most critical aspects of building a performant compound AI system. Since the output from LLMs propagate to downstream steps, i…

cs.CL2025

LAM SIMULATOR: Advancing Data Generation for Large Action Model Training via Online Exploration and Trajectory Feedback

Thai Hoang, Kung-Hsiang Huang, Shirley Kokane +12

Large Action Models (LAMs) for AI Agents offer incredible potential but face challenges due to the need for high-quality training data, especially for multi-steps tasks that involv…