Researcher, Beijing Academy of Artificial Intelligence
3 papers at NeurIPS 2025
This paper propose WebThinker, a deep research agent that empowers LRMs to autonomously search the web, navigate web pages, and draft research reports, all within its reasoning process.
We introduce InForage, an RL framework that enables LLMs to perform adaptive, multi-step retrieval by rewarding informative intermediate steps.
HawkBench is a human-labeled, multi-domain benchmark with 1,600 samples for evaluating RAG systems on diverse queries, revealing limits in generalizability and the need for adaptive strategies.
