💡 About Me
Hi! I am Xueyang Feng (冯雪扬), a PhD student at the Gaoling School of Artificial Intelligence (GSAI) of Renmin University of China, supervised by Xu Chen. Previously, I received my B.Eng. in Software Engineering from Northwestern Polytechnical University in 2023.
My research focuses on LLM Agents. My long-term goal is to build agents that understand user needs and reliably complete complex real-world tasks. I am particularly interested in:
- Long-horizon agents: Web agents, skill discovery and composition, and dynamic multi-agent orchestration.
- Personalized and interactive agents: conversational recommendation, user simulation, long-term memory, and emotional support.
- Agent post-training: agentic reinforcement learning, preference optimization, and on-policy distillation.
Feel free to contact me at xueyangfeng@ruc.edu.cn.
🔥 News
- : Our paper “From Local Skills to Long-Horizon Web Tasks: Progressive Skill Exploration for LLM Web Agents” has been accepted to NeurIPS 2026 (CCF-A). Paper.
- : Our paper “How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants” has been accepted to NeurIPS 2026 Evaluations & Datasets Track (CCF-A). Paper, Code.
- : Our paper “Need-Aware Multi-Objective Reinforcement Learning for Emotionally Intelligent LLM Agents” has been accepted to NeurIPS 2026 (CCF-A).
- : Our paper “Optimizing Multi-Turn Interactive Recommendation Agents via Generative Intrinsic Motivation” has been accepted to WWW 2026 (CCF-A). Paper, Code.
- : Our paper “Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent” has been accepted to Findings of ACL 2025 (CCF-A). Paper, Code.
- : Our paper “Improving Retrospective Language Agents via Joint Policy Gradient Optimization” has been accepted to NAACL 2025 (CCF-B). Paper, Code.
- : Our paper “Large Language Model-based Human-Agent Collaboration for Complex Task Solving” has been accepted to Findings of EMNLP 2024 (CCF-B). Paper, Code.
- : Our survey “A Survey on Large Language Model Based Autonomous Agents” has been accepted by Frontiers of Computer Science (CCF-B). Paper.
📝 Publications
* Equal contribution.
From Local Skills to Long-Horizon Web Tasks: Progressive Skill Exploration for LLM Web Agents
Xueyang Feng*, Xiaohe Bo*, Xu Chen, Quanyu Dai, Feng Wen
NeurIPS 2026 (Accepted) (CCF-A) | Paper
Proactive Agentic Orchestration
Xueyang Feng, Chaozhuo Li, Xiaohe Bo, Jiakai Tang, Chenxi Li, Qiwei Ye, Xu Chen
How Does Personalized Memory Shape LLM Behavior? Benchmarking Rational Preference Utilization in Personalized Assistants
Xueyang Feng, Weinan Gan, Xu Chen, et al.
Need-Aware Multi-Objective Reinforcement Learning for Emotionally Intelligent LLM Agents
Xiaohe Bo*, Xueyang Feng*, Rui Li, Zihang Tian, Xu Chen, Quanyu Dai
NeurIPS 2026 (CCF-A)
Optimizing Multi-Turn Interactive Recommendation Agents via Generative Intrinsic Motivation
Xueyang Feng, Jiakai Tang, Xu Chen, et al.
Expectation Confirmation Preference Optimization for Multi-Turn Conversational Recommendation Agent
Xueyang Feng, Jingsen Zhang, Jiakai Tang, et al.
Improving Retrospective Language Agents via Joint Policy Gradient Optimization
Xueyang Feng, Bo Lan, Quanyu Dai, et al.
Large Language Model-based Human-Agent Collaboration for Complex Task Solving
Xueyang Feng*, Zhi-Yuan Chen*, et al.
A Survey on Large Language Model Based Autonomous Agents
Lei Wang, Chen Ma*, Xueyang Feng*, et al.
Frontiers of Computer Science (CCF-B) | Paper
👥 Academic Service
Reviewer: ICML, NeurIPS, ICLR, ARR, WWW, TPAMI, etc.
🏆 Honors and Awards
- 2023–2025, Second-class Academic Scholarship, Renmin University of China.
- 2023, Outstanding Graduate, Shaanxi Province and Northwestern Polytechnical University.
- 2020–2021, National Scholarship.
📖 Educations
- 2023 – Present, PhD in Artificial Intelligence. Gaoling School of Artificial Intelligence, Renmin University of China. Advisor: Xu Chen. Expected graduation: June 2028.
- 2019 – 2023, B.Eng. in Software Engineering. School of Software, Northwestern Polytechnical University.
💻 Internships
- 2026.05 – Present, Beijing Academy of Artificial Intelligence, Research Intern, Beijing. Mentor: Chaozhuo Li. Research on proactive agentic orchestration and orchestration policy optimization.
- 2024.06 – 2026.03, Huawei Noah's Ark Lab, Research Intern, Shenzhen. Mentor: Quanyu Dai. Research on long-horizon Web agents, conversational recommendation, personalized memory, and emotionally intelligent assistants.