Zile Qiao

Expanding the Capability Frontier of LLM Agents with ZPD-Guided Data Synthesis

AgentFold: Long-Horizon Web Agents with Proactive Context Folding

ZeroSearch: Incentivize the Search Capability of LLMs without Searching

WebSailor-V2: Bridging the Chasm to Proprietary Agents via Synthetic Data and Scalable Reinforcement Learning

Scaling Agents via Continual Pre-training

IterResearch: Rethinking Long-Horizon Agents with Interaction Scaling

MARS: Optimizing Dual-System Deep Research via Multi-Agent Reinforcement Learning

DynamicBench: Evaluating Real-Time Report Generation in Large Language Models

End-to-End QA Construction Pipeline for Continual Pre-training of Large Language Models

C-3PO: Compact Plug-and-Play Proxy Optimization to Achieve Human-like Retrieval-Augmented Generation