My research interest focuses on LLM and Agent, with an emphasis on
fundamental capabilities (world knowledge & complex reasoning) of LLM and
agent applications, specifically:
Enhancing internal reasoning capabilities: Through continue pre-training (CPT), supervised fine-tuning
(SFT), and reinforcement learning (RL) training, expand the knowledge boundaries of LLMs and enhance
the inherent general reasoning abilities of LLMs (such as encyclopedic knowledge, mathematics, and
code).
Enhancing the ability to call external tools: Improve the ability of LLMs to call external tools (such
as code, calculators, and search engines).
Agent applications in vertical fields: Enhance the application of LLM-based agent in vertical scenarios,
such as complex structured data (such as knowledge graphs, databases, Excel spreadsheets, and tables),
general retrieval scenarios (such as AI Searcher, Deep Research), etc.
I am currently seeking job opportunities in both academic and industry. I am expected to graduate in July
2026. If you are interested in me, please do not hesitate to contact me via Email.
News
[2025-03-07] We release R1-Searcher, which is the first technical report to apply the RL of the R1 paradigm to the RAG scenario. It has achieved significant performance improvements across multiple evaluation datasets, marking an important step towards Deep Research!
Experience
2025/01 - present: seed-ByteDance (字节跳动) LLM Research Intern
2024/10 - 2024/12: BAAI (智源研究院) LLM Research Intern
2023/07 - 2024/10: Boss Zhipin (BOSS直聘) LLM Research Intern