LLM-SMAC: Solving Multi-Agent Decision-Making Tasks via LLM Decision Tree Code Generation

StarCraft Multi-Agent Challenge (SMAC) has become a widely used benchmark in multi-agent systems, where agents must control allied units to defeat enemy forces. Traditional MARL methods typically require millions of environment interactions to train parametric policies, which are often non-interpretable and exhibit limited transferability. In this paper, we introduce LLM-SMAC, a closedloop Planner–Coder–Critic framework. Given task descriptions, the LLM planner first generates a decision-tree strategy, which is translated into executable code by the coder. The generated scripts are executed in the environment, and reward signals and runtime feedback are fed back to a critic module for self-reflection and iterative refinement. Through this closed-loop process, this mechanism progressively improves both strategy design and code implementation without large-scale environment exploration. We evaluate our method on the original SMAC tasks and the results show that LLM- SMAC can produce high-quality, interpretable decision trees with minimal interaction, while demonstrating strong transferability across homogeneous SMAC environments without modification.

Authors

• Yue Deng Zhongguancun Academy
• Weiyu Ma Chinese Academy of Sciences
• Yuxin Fan Xi'an Jiaotong University
• Ruyi Song Zhejiang University
• Yin Zhang Zhejiang University
• Haifeng Zhang Chinese Academy of Sciences
• Jian Zhao Zhongguancun Academy

Keywords

• Decision-making
• Decision Tree Script
• LLM
• SMAC