About
I am a second-year PhD student at the Gaoling School of Artificial Intelligence (GSAI), Renmin University of China (RUC), supervised by Prof. Zhicheng Dou. I received my bachelor’s degree from RUC in 2025.
My recent research focuses on long-horizon agents, including self-evolving agents, agent memory, AutoResearch agents, and ML Coding.
I am currently a research intern at the LLM Center of the Shanghai Artificial Intelligence Laboratory, mentored by Prof. Tao Gui. My work there focuses on ML Coding.
Feel free to contact me if you are interested in related topics or potential collaborations!
🔥 News
🧩 We released Repo-To-Skill, which distills GitHub repositories into reusable skills for AI research agents.
🚀 I joined the LLM Center at Shanghai AI Laboratory as a research intern, working on ML Coding with Prof. Tao Gui.
📚 We released AREX and OPOD, and our survey Towards Long-Horizon Agents is now available.
🔬 We released Arbor, VeriGraph, and MemoPilot for autonomous research, verifiable data analysis, and test-time agent learning.
🤖 We released AgentFugue, SAM, and our work on defending agentic harnesses against persistent-control attacks.
🎉 CompassMem was accepted to ACL 2026 Findings!
🧠 Our MemSifter paper is now available on arXiv.
✨ I started a research internship at the Information Retrieval and Knowledge Computing Group, BAAI.
📖 We released Memory in the Age of AI Agents, a survey on agent memory.
🎓 Graduated from RUC GSAI with a bachelor's degree.
💼 Experience
📑 Selected Publications
View All →
Repo-To-Skill: Distilling GitHub Repositories Into AI4AI Skills
Jianlyu Chen*, Yuyang Hu*, Hongjin Qian*, Jiawei Liu*, et al.
CoRR 2026
DisCo distills operational knowledge from machine-learning repositories into compact, verified skills that autonomous research agents can reuse across tasks.
Toward Generalist Autonomous Research via Hypothesis-Tree Refinement
Jiajie Jin*, Yuyang Hu*, Kai Qiu, Qi Dai, et al.
CoRR 2026
Arbor combines a long-lived coordinator, isolated executors, and persistent hypothesis-tree refinement for cumulative autonomous research.
AgentFugue: Agent Scaling for Long-Horizon Tasks through Collective Reasoning
Yuyang Hu, Hongjin Qian, Shuting Wang, Jiongnan Liu, et al.
CoRR 2026
A collective reasoning framework that lets peer agents share reusable intermediate reasoning through a shared reasoning hub for long-horizon tasks.
SAM: State-Adaptive Memory for Long-Horizon Reasoning Agent
Yuyang Hu, Hongjin Qian, Shuting Wang, Jiongnan Liu, et al.
CoRR 2026
A state-adaptive memory framework that preserves raw trajectory pages while using compact memory cues for intent-driven recall in long-horizon agents.
Memory Matters More: Event-Centric Memory as a Logic Map for Agent Searching and Reasoning
Yuyang Hu, Jiongnan Liu, Jiejun Tan, Yutao Zhu, et al.
ACL Findings 2026
An event-centric memory framework that organizes agent experiences into an event graph for logic-aware memory search and reasoning.
🎓 Education
Gaoling School of Artificial Intelligence · Ph.D. Student
Gaoling School of Artificial Intelligence · Bachelor's Degree