Several papers accepted by EMNLP 2025 and ACL 2025 main conference, including CAFE, StickerTTS, ManuSearch, R1-Searcher++, SimpleDeepSearcher, YuLan-Mini, Llama-3-SynE, KG-Agent, and LongReD. Also released several research projects such as ManuSearch, SimpleDeepSearcher, and R1-Searcher.
Research Experience
Current research includes: enhancing the internal reasoning capabilities of LLMs through continuous pre-training (CPT), supervised fine-tuning (SFT), and reinforcement learning (RL), improving the ability of LLMs to call external tools, and exploring the application of LLM-based agents in various scenarios.
Education
Fourth-year Ph.D. student at Gaoling School of Artificial Intelligence, Renmin University of China (expected to graduate in June 2026), supervised by Prof. Xin Zhao. Previously, obtained a bachelor's degree from the University of Electronic Science and Technology of China in July 2021.
Background
Research interests: Natural Language Processing, Large Language Models (LLMs), and Agents. Specifically focused on the fundamental capabilities of LLMs (such as world knowledge and complex reasoning) and agent applications.
Miscellany
Currently seeking job opportunities in both academia and industry.