Can Lv (吕灿 in Chinese) is currently a first-year M.S. student at the School of Artificial Intelligence, Beihang University (BUAA), supervised by Prof. Shiji Zhou. He received his bachelor’s degree from the School of Computer Science, Beijing University of Posts and Telecommunications (BUPT). He is currently an AI intern at Unity and was previously an AI intern at Huawei.

His research focuses on

• Agentic Reinforcement Learning (AgenticRL)
• Agent Harness
• Recursive Self-Improvement (RSI)

🔥 News

• 2026.09:   GEAR and HarnessForge are selected as Oral papers at EMNLP 2026.
• 2026.08:   GEAR and HarnessForge are accepted by EMNLP 2026.
• 2026.08:   TRCA is released on arXiv.
• 2026.06:   GEAR and HarnessForge are released on arXiv.
• 2026.03:   All-Mem is released on arXiv.

📝 Publications

• arXiv 2026 Beyond Timestamps: Decision-Aligned On-Policy Distillation for Long-Horizon Agents
  Mingju Chen^*, Can Lv^*, Jinrong Liu, Huan Zhang, Heng Chang, Shiji Zhou | Code

• EMNLP 2026 Oral Mitigating False Credit Propagation: Probabilistic Graphical Reward Aggregation for Rubric-Based Reinforcement Learning
  Can Lv, Mingju Chen, Heng Chang, Shiji Zhou | Code

• EMNLP 2026 Oral HarnessForge: Joint Harness and Policy Evolution for Adaptive Agent Systems
  Mingju Chen, Can Lv, Guibin Zhang, Heng Chang, Shiji Zhou | Code

• arXiv 2026 All-Mem: Agentic Lifelong Memory via Dynamic Topology Evolution
  Can Lv, Heng Chang, Shengyu Tao, Mingju Chen, Zhaoxin Fan, Ziwei Zhang, Yuchen Guo, Shiji Zhou | Code

• arXiv 2026 TRCA: Transition-wise Rubric Credit Assignment for Long-horizon LLM Agents
  Huan Zhang, Mingju Chen, Dongxu Zhou, Can Lv, Heng Chang, Sen Cui, Faguo Wu, Shiji Zhou | Code

^* Equal contribution.

🎖 Honors and Awards

• 2024.12, National Scholarship.
• 2023.12, National Scholarship.

📖 Educations

• M.S. student in the School of Artificial Intelligence, Beihang University. Advisor: Prof. Shiji Zhou.
• Bachelor’s degree from the School of Computer Science, Beijing University of Posts and Telecommunications.

💻 Internships

• 2026.08 - Present, AI Intern, Unity.
• 2025.12 - 2026.08, AI Intern, Huawei.