Da Yin

RefTool: Reference-Guided Tool Creation for Knowledge-Intensive Reasoning

Learning to Interrupt in Language-based Multi-agent Communication

FronTalk: Benchmarking Front-End Development as Conversational Code Generation with Multi-Modal Feedback

DialectGen: Benchmarking and Improving Dialect Robustness in Multimodal Generation

LLMs as Scalable, General-Purpose Simulators For Evolving Digital Agent Training

Bridging the Data Provenance Gap Across Text, Speech, and Video

QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search

Q* Agent: Optimizing Language Agents with Q-Guided Exploration