I received my Master degree from Zhejiang University in March 2026, and will start my Ph.D. in Computer Science and Technology at Zhejiang University in September 2026, jointly trained with Shanghai AI Laboratory. Currently, I am an intern researcher at Shanghai AI Laboratory.

My research interests lie in continual learning, large language models (LLMs), and agents. I am particularly interested in building agents that can learn from it’s own experience, and improve through interaction over time.

News

• 2026.03: I received my Master degree from Zhejiang University.
• 2026: One paper was accepted to ICML 2026, and one paper was accepted to ACL 2026.
• 2025: One paper was accepted to AAAI 2026.

Selected Publications

Selected papers are shown below. * denotes equal contribution. For the full publication list, please see Publications.

Agent

ICML 2026 EvolveR: Self-Evolving LLM Agents through an Experience-Driven Lifecycle

Rong Wu*, Xiaoman Wang*, Jianbiao Mei, Pinlong Cai, Daocheng Fu, Cheng Yang, Licheng Wen, Xuemeng Yang, Yufan Shen, et al.

Code HuggingFace

• A closed-loop experience lifecycle that enables LLM agents to distill reusable strategic principles offline and retrieve them during online interaction.

ACL 2026 Findings The Agent’s First Day: Benchmarking Learning, Exploration, and Scheduling in the Workplace Scenarios

Daocheng Fu*, Jianbiao Mei*, Rong Wu*, Xuemeng Yang, Jia Xu, Ding Wang, Pinlong Cai, Yong Liu, Licheng Wen, Botian Shi.

Code HuggingFace

• Introduces Trainee-Bench, a dynamic benchmark for evaluating scheduling, exploration, and continual learning in workplace scenarios.

RAG

AAAI 2026 LeanRAG: Knowledge-Graph-based Generation with Semantic Aggregation and Hierarchical Retrieval

Yaoze Zhang*, Rong Wu*, Pinlong Cai, Xiaoman Wang, Guohang Yan, Song Mao, Ding Wang, Botian Shi.

Code HuggingFace

• A hierarchical KG-RAG framework with semantic aggregation and structure-guided retrieval to reduce redundancy.

Preprint KG-Traces: Enhancing Large Language Models with Knowledge Graph-Constrained Trajectory Reasoning and Attribution Supervision

Rong Wu, Pinlong Cai, Jianbiao Mei, Licheng Wen, Tao Hu, Xuemeng Yang, Daocheng Fu, Botian Shi

Code HuggingFace

• Supervises LLM reasoning with KG-constrained trajectories and attribution-aware explanations for traceable reasoning.

Ai4sci

• Energy A Transferable Federated Learning Approach for Wind Power Prediction Based on Active Privacy Clustering and Knowledge Merge, Feiyun Cong, Rong Wu, Wei Zhong, Xiaojie Lin.
• ASME 2024 An Ultra-Short-Term Power Prediction Method for Wind Farms in Northwest China Based on Federated Learning, Rong Wu, Xiaojie Lin, Feiyun Cong, Wei Zhong.

Education

• 2023 - 2026, Master in Smart Energy (Power Engineering), College of Excellent Engineers, Zhejiang University.
• 2019 - 2023, Bachelor in Energy and Power Engineering, Nanjing University of Aeronautics and Astronautics.

Experience

• 2025.02 - Present, Research Intern, Shanghai AI Laboratory.
• 2023.12 - 2024.09, Research Intern, Alibaba Cloud