Hangyu Mao

Kuaishou (China)

Papers

2

Total Citations

5

H-Index

2

About

Hangyu Mao is a leading researcher at the intersection of large language models (LLMs), multi-agent systems, and explainable deep reinforcement learning (DRL). His work addresses critical challenges in scaling AI decision-making, particularly the hallucination and coordination issues that arise when deploying LLM-based agents in large-scale environments. In his highly cited 2023 paper, Mao introduced an actor-critic framework that integrates LLMs into multi-agent systems, offering a novel solution for robust, large-scale decision-making. This work has garnered 3 citations and is recognized for bridging the gap between language model reasoning and multi-agent coordination. More recently, Mao’s 2025 paper, "SkillTree," tackles the transparency problem in DRL by proposing a skill-based, decision-tree approach that makes long-horizon control tasks explainable—a crucial advancement for safety-critical and human-interactive domains. With 2 citations already, this work underscores his commitment to building AI systems that are not only powerful but also interpretable. Mao’s contributions are shaping the future of autonomous agents, making complex AI systems more reliable, scalable, and understandable for real-world applications.

Research Focus

Key Achievements

2
H-Index
2
Papers
5
Total Citations
3
Avg Citations/Paper
🏆 Most Cited Paper
Controlling Large Language Model-based Agents for Large-Scale Decision-Making: An Actor-Critic Approach
3 citations · 2023
📈 Most Prolific Year: 2023 (1 Papers)
🤝 Key Collaborators: 16
🏛 Institutions: Kuaishou (China)

Top Papers

  1. 1
  2. 2

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 12 days ago