# TacticCraft: Natural Language-Driven Tactical Adaptation for StarCraft II

arXiv: https://arxiv.org/abs/2507.15618 · HTML: https://mlsanity.com/paper/2507.15618/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 9 of its 21 references that are in the map.
- First posted on arXiv 21 Jul 2025.

## Builds on (most cited first, 9 of 9)

- [Parameter-Efficient Transfer Learning for NLP](https://mlsanity.com/paper/1902.00751/) (2019)
- [Large Language Models](https://mlsanity.com/paper/2307.05782/) (2023)
- [StarCraft II: A New Challenge for Reinforcement Learning](https://mlsanity.com/paper/1708.04782/) (2017)
- [Multiagent Bidirectionally-Coordinated Nets: Emergence of Human-level Coordination in Learning to Play StarCraft Combat Games](https://mlsanity.com/paper/1703.10069/) (2017)
- [SCC: an efficient deep reinforcement learning agent mastering the game of StarCraft II](https://mlsanity.com/paper/2012.13169/) (2020)
- [TStarBot-X: An Open-Sourced and Comprehensive Study for Efficient League Training in StarCraft II Full Game](https://mlsanity.com/paper/2011.13729/) (2020)
- [On Efficient Reinforcement Learning for Full-length Game of StarCraft II](https://mlsanity.com/paper/2209.11553/) (2022)
- [An Introduction of mini-AlphaStar](https://mlsanity.com/paper/2104.06890/) (2021)
- [LLM-PySC2: Starcraft II learning environment for Large Language Models](https://mlsanity.com/paper/2411.05348/) (2024)

## Built on by (most cited first, 2 of 2)

- [The Landscape of Agentic Reinforcement Learning for LLMs: A Survey](https://mlsanity.com/paper/2509.02547/) (2025)
- [Self-Improvement of Large Language Models: A Technical Overview and Future Outlook](https://mlsanity.com/paper/2603.25681/) (2026)

## Abstract (arXiv)

We present an adapter-based approach for tactical conditioning of StarCraft II AI agents. Current agents, while powerful, lack the ability to adapt their strategies based on high-level tactical directives. Our method freezes a pre-trained policy network (DI-Star) and attaches lightweight adapter modules to each action head, conditioned on a tactical tensor that encodes strategic preferences. By training these adapters with KL divergence constraints, we ensure the policy maintains core competencies while exhibiting tactical variations. Experimental results show our approach successfully modulates agent behavior across tactical dimensions including aggression, expansion patterns, and technology preferences, while maintaining competitive performance. Our method enables flexible tactical control with minimal computational overhead, offering practical strategy customization for complex real-time strategy games.