Sunhao Dai

Information Gain-based Policy Optimization: A Simple and Effective Approach for Multi-Turn Search Agents

From Exploration to Mastery: Enabling LLMs to Master Tools via Self-Driven Interactions

GUI-G1: Understanding R1-Zero-Like Training for Visual Grounding in GUI Agents

Perplexity Trap: PLM-Based Retrievers Overrate Low Perplexity Documents

Length-Induced Embedding Collapse in Transformer-based Models