collaborators

5 papers

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…

cs.CL2025

Text2Data: Low-Resource Data Generation with Textual Control

Shiyu Wang, Yihao Feng, Tian Lan +6

Natural language serves as a common and straightforward signal for humans to interact seamlessly with machines. Recognizing the importance of this interface, the machine learning c…

cs.AI2024

AgentOhana: Design Unified Data and Training Pipeline for Effective Agent Learning

Jianguo Zhang, Tian Lan, Rithesh Murthy +15

Autonomous agents powered by large language models (LLMs) have garnered significant research attention. However, fully harnessing the potential of LLMs for agent-based tasks presen…

cs.AI2024

PRACT: Optimizing Principled Reasoning and Acting of LLM Agent

Zhiwei Liu, Weiran Yao, Jianguo Zhang +13

We introduce the Principled Reasoning and Acting (PRAct) framework, a novel method for learning and enforcing action principles from trajectory data. Central to our approach is the…