# SMAC-R1: The Emergence of Intelligence in Decision-Making Tasks

arXiv: https://arxiv.org/abs/2410.16024 · HTML: https://mlsanity.com/paper/2410.16024/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 29 of its 37 references that are in the map.
- First posted on arXiv 21 Oct 2024.

## Builds on (most cited first, 29 of 29)

- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Training language models to follow instructions with human feedback](https://mlsanity.com/paper/2203.02155/) (2022)
- [LLaMA: Open and Efficient Foundation Language Models](https://mlsanity.com/paper/2302.13971/) (2023)
- [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://mlsanity.com/paper/2402.03300/) (2024)
- [Qwen Technical Report](https://mlsanity.com/paper/2309.16609/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [HybridFlow: A Flexible and Efficient RLHF Framework](https://mlsanity.com/paper/2409.19256/) (2024)
- [LlamaFactory: Unified Efficient Fine-Tuning of 100+ Language Models](https://mlsanity.com/paper/2403.13372/) (2024)
- [Qwen2.5-Coder Technical Report](https://mlsanity.com/paper/2409.12186/) (2024)
- [DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence](https://mlsanity.com/paper/2401.14196/) (2024)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [QMIX: Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/1803.11485/) (2018)
- [The StarCraft Multi-Agent Challenge](https://mlsanity.com/paper/1902.04043/) (2019)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [Executable Code Actions Elicit Better LLM Agents](https://mlsanity.com/paper/2402.01030/) (2024)
- [Value-Decomposition Networks For Cooperative Multi-Agent Learning](https://mlsanity.com/paper/1706.05296/) (2017)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [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)
- [StarCraft II: A New Challenge for Reinforcement Learning](https://mlsanity.com/paper/1708.04782/) (2017)
- [QPLEX: Duplex Dueling Multi-Agent Q-Learning](https://mlsanity.com/paper/2008.01062/) (2020)
- [Language Agents with Reinforcement Learning for Strategic Play in the Werewolf Game](https://mlsanity.com/paper/2310.18940/) (2023)
- [Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach](https://mlsanity.com/paper/2312.11865/) (2023)
- [PokeLLMon: A Human-Parity Agent for Pokemon Battles with Large Language Models](https://mlsanity.com/paper/2402.01118/) (2024)
- [Learning to Discuss Strategically: A Case Study on One Night Ultimate Werewolf](https://mlsanity.com/paper/2405.19946/) (2024)
- [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)
- [Efficient Reinforcement Learning for StarCraft by Abstract Forward Models and Transfer Learning](https://mlsanity.com/paper/1903.00715/) (2019)
- [An Introduction of mini-AlphaStar](https://mlsanity.com/paper/2104.06890/) (2021)

## Built on by (most cited first, 6 of 6)

- [HiMA-Ecom: Enabling Joint Training of Hierarchical Multi-Agent E-commerce Assistants](https://mlsanity.com/paper/2506.19846/) (2025)
- [SMAC-Hard: Enabling Mixed Opponent Strategy Script and Self-play on SMAC](https://mlsanity.com/paper/2412.17707/) (2024)
- [EvoCurr: Self-evolving Curriculum with Behavior Code Generation for Complex Decision-making](https://mlsanity.com/paper/2508.09586/) (2025)
- [PROF: An LLM-based Reward Code Preference Optimization Framework for Offline Imitation Learning](https://mlsanity.com/paper/2511.13765/) (2025)
- [Retrieval Augmented Learning: A Retrial-based Large Language Model Self-Supervised Learning and Autonomous Knowledge Generation](https://mlsanity.com/paper/2505.01073/) (2025)
- [Compiled Agency: Frontier General-Purpose Coding Agents Build Winning Game Players from Bare Interaction - from Flappy Bird to StarCraft II and Civilization](https://mlsanity.com/paper/2609.18996/) (2026)

## Abstract (arXiv)

StarCraft Multi-Agent Challenge (SMAC) has been one of the most commonly used experimental environments in multi-agent reinforcement learning (MARL), where the specific task is to control a set number of allied units to defeat enemy forces. Traditional MARL algorithms often require interacting with the environment for millions of steps to train a parametric model, of which the resulting policies are typically non-interpretable with weak transferability. In this paper, we introduce SMAC-R1 which is based on the Qwen2.5-7B-Base LLM distilled from DeepSeek-Coder-v2.5-236B. Similar to online reinforcement learning after behavior cloning in offline learning process, in our pipeline, agents leverage the DeepSeek LLM to generate decision tree code by providing task descriptions, and the agents are further self-reflected using feedback from the rewards provided by the environment. Based on that, we augment the generated scripts to fine-tune a small LLM, Qwen2.5-7B-Base, to distill the decision-making ability via Supervised Fine-Tuning (SFT) and enhance the script generation ability by the Group Relative Policy Optimization (GRPO) algorithm. We conduct experiments in the original 23 SMAC tasks and 10 newly-designed tasks to demonstrate that our method can produce high-quality, interpretable decision trees with minimal environmental exploration. Moreover, these scripts exhibit strong transferability, successfully applying to homogeneous SMAC environments without modification. We believe this approach offers a new direction for solving decision-making tasks and domain-specific LLM training pipelines in the future.