Xiangru Tang

A new framework simplifies creating autonomous language agents for diverse applications.

This study examines LLM capabilities in producing structured data accurately.

Examining vulnerabilities and safety strategies for LLM-powered scientific agents.

A tool designed to improve data science tasks through dynamic planning and error checking.

AI is changing the way new drugs are developed, making it faster and more efficient.

This article discusses issues and best practices for evaluating language models.

Data contamination affects the evaluation of large language models significantly.

This article discusses new approaches to improve predictions in chemical reactions using technology.

A new benchmark assesses models for verifying financial claims in complex documents.

ChemSafetyBench tests chatbots on chemical safety and knowledge.