# SC-Phi2: A Fine-tuned Small Language Model for StarCraft II Macromanagement Tasks

arXiv: https://arxiv.org/abs/2409.18989 · HTML: https://mlsanity.com/paper/2409.18989/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 12 of its 18 references that are in the map.
- First posted on arXiv 17 Sep 2024.

## Builds on (most cited first, 12 of 12)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale](https://mlsanity.com/paper/2010.11929/) (2020)
- [Ghost in the Minecraft: Generally Capable Agents for Open-World Environments via Large Language Models with Text-based Knowledge and Memory](https://mlsanity.com/paper/2305.17144/) (2023)
- [A Survey on Large Language Model-Based Game Agents](https://mlsanity.com/paper/2404.02039/) (2024)
- [Large Language Models and Games: A Survey and Roadmap](https://mlsanity.com/paper/2402.18659/) (2024)
- [Can Large Language Models Reason and Plan?](https://mlsanity.com/paper/2403.04121/) (2024)
- [Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach](https://mlsanity.com/paper/2312.11865/) (2023)
- [TinyGPT-V: Efficient Multimodal Large Language Model via Small Backbones](https://mlsanity.com/paper/2312.16862/) (2023)
- [MineDreamer: Learning to Follow Instructions via Chain-of-Imagination for Simulated-World Control](https://mlsanity.com/paper/2403.12037/) (2024)
- [Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks](https://mlsanity.com/paper/2303.16563/) (2023)
- [MSC: A Dataset for Macro-Management in StarCraft II](https://mlsanity.com/paper/1710.03131/) (2017)
- [Leveraging Transformers for StarCraft Macromanagement Prediction](https://mlsanity.com/paper/2110.05343/) (2021)

## Built on by (most cited first, 1 of 1)

- [Shall We Play a Game? Language Models for Open-ended Wargames](https://mlsanity.com/paper/2509.17192/) (2025)

## Abstract (arXiv)

This paper introduces SC-Phi2, a fine-tuned StarCraft II small language model for macromanagement tasks. Small language models, like Phi2, Gemma, and DistilBERT, are streamlined versions of large language models (LLMs) with fewer parameters that require less power and memory to run. To teach Microsoft's Phi2 model about StarCraft, we create a new SC2 text dataset with information about StarCraft races, roles, and actions and use it to fine-tune Phi-2 with self-supervised learning. We pair this language model with a Vision Transformer (ViT) from the pre-trained BLIP-2 (Bootstrapping Language Image Pre-training) model, fine-tuning it on the MSC replay dataset. This enables us to construct dynamic prompts that include visual game state information. Unlike the large models used in StarCraft LLMs such as GPT-3.5, Phi2 is trained primarily on textbook data and contains little inherent knowledge of StarCraft II beyond what is provided by our training process. By using LoRA (Low-rank Adaptation) and quantization, our model can be trained on a single GPU. We demonstrate that our model performs well at micromanagement tasks such as build order and global state prediction with a small number of parameters.