CV

📝 A PDF version of my CV is available here.

Education

• Ph.D. in Control Science and Engineering, Tsinghua University, Department of Automation, 2023 - present.
  • Research: reinforcement learning and large language models.
  • Advisors: Prof. Qing-Shan Jia.
• B.Eng. in Computer Science, Southeast University, Gifted Young Class, 2019 - 2023.
  • Rank: 3 / 275 (top 1.5%).

Research Interests

• Reinforcement learning (RL): preference-based RL, skill discovery, multi-objective RL, model-based RL, multi-agent RL;
• Large language models (LLMs): LLMs for long-horizon decision-making;
• Real-world RL applications: data-center cooling control, autonomous driving.

Honors & Awards

• Outstanding WiRA Student Paper Award, IEEE CASE 2025 (2025)
• Tsinghua University Comprehensive Scholarship, First Class (2025, 2024)
• Most Influential Undergraduate, Southeast University (2023)
• President’s Scholarship, Southeast University (2021)
• National Scholarship (2020)

Publications

Learning Interpretable Index Policies via LLM-Driven Zero-Order Optimization

[1] Yao Luan*, Ni Mu*, Qing-Shan Jia. (2026). "Learning Interpretable Index Policies via LLM-Driven Zero-Order Optimization." IEEE CASE 2026.

COLLIE: Guiding Skill Discovery in Semantically Coherent Latent Space

[2] Yao Luan*, Ni Mu*, Hanfei Ge, Yiqin Yang, Bo Xu, Qing-Shan Jia. (2026). "COLLIE: Guiding Skill Discovery in Semantically Coherent Latent Space." ICML 2026.

GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent System

[3] Yiqin Yang*, Xu Yang*, Yuhua Jiang, Ni Mu, Hao Hu, Runpeng Xie, Ziyou Zhang, Siyuan Li, Yuan-Hua Ni, Qianchuan Zhao, Bo Xu. (2026). "GlobeDiff: State Diffusion Process for Partial Observability in Multi-Agent System." ICLR 2026.

MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios

[4] Xuantang Xiong*, Ni Mu*, Runpeng Xie, Senhao Yang, Yaqing Wang, Lexiang Wang, Yao Luan, Siyuan Li, Shuang Xu, Yiqin Yang, Bo Xu. (2026). "MrCoM: A Meta-Regularized World-Model Generalizing Across Multi-Scenarios." AAAI 2026.

Covering the Pareto Frontier with LLM-Coordinated Interpretable Policy Library

[5] Ni Mu*, Yao Luan*, Qing-Shan Jia. (2026). "Covering the Pareto Frontier with LLM-Coordinated Interpretable Policy Library." 23rd IFAC World Congress (IFAC 2026).

MAGPIE: Utilizing Agent-Specific Preferences for Multi-Agent Reinforcement Learning

[6] Ni Mu*, Yao Luan*, Qing-Shan Jia. (2025). "MAGPIE: Utilizing Agent-Specific Preferences for Multi-Agent Reinforcement Learning." 2025 China Automation Congress (CAC).

LLM-Empowered Knowledge Graph Construction for Optimization Formalization in Smart Manufacturing

[7] Ni Mu, Zeyuan Liu, Yuhang Zhu, Qing-Shan Jia. (2025). "LLM-Empowered Knowledge Graph Construction for Optimization Formalization in Smart Manufacturing." 2025 China Automation Congress (CAC).

DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning

[8] Runpeng Xie*, Quanwei Wang*, Hao Hu, Zherui Zhou, Ni Mu, Xiyun Li, Yiqin Yang, Shuang Xu, Qianchuan Zhao, Bo Xu. (2025). "DAIL: Beyond Task Ambiguity for Language-Conditioned Reinforcement Learning." NeurIPS 2025.

STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning

[9] Yao Luan*, Ni Mu*, Yiqin Yang, Bo Xu, Qing-Shan Jia. (2025). "STAIR: Addressing Stage Misalignment through Temporal-Aligned Preference Reinforcement Learning." NeurIPS 2025.

SunTzu: A Long-Horizon Decision Making Benchmark for Large Language Models

[10] Pengbo Shen*, Yaqing Wang*, Ni Mu*, Yao Luan, Runpeng Xie, Senhao Yang, Lexiang Wang, Hao Hu, Shuang Xu, Yiqin Yang, Bo Xu. (2025). "SunTzu: A Long-Horizon Decision Making Benchmark for Large Language Models." Submitted to NeurIPS 2026.

Addressing Coupling in Restless Multi-Armed Bandits by Finetuning Whittle Index

[11] Yao Luan, Ni Mu, Qing-Shan Jia. (2025). "Addressing Coupling in Restless Multi-Armed Bandits by Finetuning Whittle Index." IEEE 21st International Conference on Automation Science and Engineering (CASE 2025).

Safety-Guaranteed Policy Composition Via Generalized Policy Improvement for Autonomous Vehicles

[12] Ni Mu, Yao Luan, Qing-Shan Jia. (2025). "Safety-Guaranteed Policy Composition Via Generalized Policy Improvement for Autonomous Vehicles." IEEE 21st International Conference on Automation Science and Engineering (CASE 2025).

Preference-based Multi-Objective Reinforcement Learning

[13] Ni Mu*, Yao Luan*, Qing-Shan Jia. (2025). "Preference-based Multi-Objective Reinforcement Learning." IEEE Transactions on Automation Science and Engineering.

CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries

[14] Ni Mu*, Hao Hu*, Xiao Hu, Yiqin Yang, Bo Xu, Qing-Shan Jia. (2025). "CLARIFY: Contrastive Preference Reinforcement Learning for Untangling Ambiguous Queries." ICML 2025.

S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning

[15] Ni Mu*, Yao Luan*, Yiqin Yang, Bo Xu, Qing-Shan Jia. (2025). "S-EPOA: Overcoming the Indistinguishability of Segments with Skill-Driven Preference-Based Reinforcement Learning." IJCAI 2025.

A Transformer-based Thermal Surrogate Model for Cooling Control in Data Centers

[16] Hanchen Zhou, Ni Mu, Qing-Shan Jia. (2025). "A Transformer-based Thermal Surrogate Model for Cooling Control in Data Centers." IEEE Robotics and Automation Letters.

Preference-Based Multi-Objective Reinforcement Learning with Explicit Reward Modeling

[17] Ni Mu, Yao Luan, Qing-Shan Jia. (2024). "Preference-Based Multi-Objective Reinforcement Learning with Explicit Reward Modeling." 2024 China Automation Congress (CAC).

Large-scale data center cooling control via sample-efficient reinforcement learning

[18] Ni Mu, Xiao Hu, Qing-Shan Jia, Xun Zhu, Xiao He. (2024). "Large-scale data center cooling control via sample-efficient reinforcement learning." IEEE 20th International Conference on Automation Science and Engineering (CASE 2024).

Integrating mechanism and data: Reinforcement learning based on multi-fidelity model for data center cooling control

[19] Ni Mu, Xiao Hu, Qing-Shan Jia. (2023). "Integrating mechanism and data: Reinforcement learning based on multi-fidelity model for data center cooling control." 2023 China Automation Congress (CAC).

E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance

[20] Can Chang, Ni Mu, Jiajun Wu, Ling Pan, Huazhe Xu. (2022). "E-MAPP: Efficient Multi-Agent Reinforcement Learning with Parallel Program Guidance." NeurIPS 2022.

Contact

• Email: mn23 AT mails.tsinghua.edu.cn
• Location: Beijing, China
• Links: Google Scholar · GitHub