# LLM-PySC2: Starcraft II learning environment for Large Language Models

arXiv: https://arxiv.org/abs/2411.05348 · HTML: https://mlsanity.com/paper/2411.05348/

## Key facts

- Cited by 9 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 8 Nov 2024.

## Built on by (most cited first, 9 of 9)

- [A Survey on Large Language Model-Based Social Agents in Game-Theoretic Scenarios](https://mlsanity.com/paper/2412.03920/) (2024)
- [Stop Reducing Responsibility in LLM-Powered Multi-Agent Systems to Local Alignment](https://mlsanity.com/paper/2510.14008/) (2025)
- [AVA: Attentive VLM Agent for Mastering StarCraft II](https://mlsanity.com/paper/2503.05383/) (2025)
- [TacticCraft: Natural Language-Driven Tactical Adaptation for StarCraft II](https://mlsanity.com/paper/2507.15618/) (2025)
- [Memory-Augmented State Machine Prompting: A Novel LLM Agent Framework for Real-Time Strategy Games](https://mlsanity.com/paper/2510.18395/) (2025)
- [Retrieval Augmented Learning: A Retrial-based Large Language Model Self-Supervised Learning and Autonomous Knowledge Generation](https://mlsanity.com/paper/2505.01073/) (2025)
- [LLM-Cave: A benchmark and light environment for large language models reasoning and decision-making system](https://mlsanity.com/paper/2511.22598/) (2025)
- [World Models for Policy Refinement in StarCraft II](https://mlsanity.com/paper/2602.14857/) (2026)
- [LLMs Are Not Good Strategists, Yet Memory-Enhanced Agency Boosts Reasoning](https://mlsanity.com/paper/2608.12626/) (2026)

## Abstract (arXiv)

The tremendous potential has been demonstrated by large language models (LLMs) in intelligent decision-making problems, with unprecedented capabilities shown across diverse applications ranging from gaming AI systems to complex strategic planning frameworks. However, the StarCraft II platform, which has been widely adopted for validating decision-making algorithms in the past decade, has not yet provided substantial support for this emerging domain. To address issues that LLMs cannot interface with the hundreds of actions of the pysc2 backend and the lack of native support for multi-agent (MA) collaboration, we propose the LLM-PySC2 environment. This is the first environment that offers LLMs the complete pysc2 action space with sufficient multi-modal information and game Wiki knowledge. With an asynchronous query architecture, the environment efficiently interacts with LLMs that maintain a constant latency regardless of the scale of the agents' population. In the experiments, we evaluated LLMs' decision-making performance in both the macro-decision and micro-operation scenarios, with traditional StarCraft II Multi-Agent Challenge (SMAC) tasks and a series of new proposed. Results indicate that LLMs possess the potential to achieve victories in complex scenarios but cannot constantly generate correct decisions, especially in the recovered pysc2 action space and MA settings. Without task-relevant instructions, the pre-trained models suffer from issues such as hallucinations and inefficient collaboration. Our findings suggest that StarCraft II still challenges in the era of large models, revealing that there is a lot to do to develop an advanced LLM decision-making system, and the proposed LLM-PySC2 environment will support future development of LLM-based decision-making solutions.