# COA-GPT: Generative Pre-trained Transformers for Accelerated Course of Action Development in Military Operations

arXiv: https://arxiv.org/abs/2402.01786 · HTML: https://mlsanity.com/paper/2402.01786/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 14 of its 37 references that are in the map.
- First posted on arXiv 1 Feb 2024.

## Builds on (most cited first, 14 of 14)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [Asynchronous Methods for Deep Reinforcement Learning](https://mlsanity.com/paper/1602.01783/) (2016)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [StarCraft II: A New Challenge for Reinforcement Learning](https://mlsanity.com/paper/1708.04782/) (2017)
- [Grounding Language with Visual Affordances over Unstructured Data](https://mlsanity.com/paper/2210.01911/) (2022)
- [STEVE-1: A Generative Model for Text-to-Behavior in Minecraft](https://mlsanity.com/paper/2306.00937/) (2023)
- [DisasterResponseGPT: Large Language Models for Accelerated Plan of Action Development in Disaster Response Scenarios](https://mlsanity.com/paper/2306.17271/) (2023)
- [Graph Neural Network Enhanced Language Models for Efficient Multilingual Text Classification](https://mlsanity.com/paper/2203.02912/) (2022)
- [On games and simulators as a platform for development of artificial intelligence for command and control](https://mlsanity.com/paper/2110.11305/) (2021)
- [Learning to Guide Multiple Heterogeneous Actors from a Single Human Demonstration via Automatic Curriculum Learning in StarCraft II](https://mlsanity.com/paper/2205.05784/) (2022)

## Built on by (most cited first, 12 of 12)

- [On Large Language Models in National Security Applications](https://mlsanity.com/paper/2407.03453/) (2024)
- [Multi-RAG: A Multimodal Retrieval-Augmented Generation System for Adaptive Video Understanding](https://mlsanity.com/paper/2505.23990/) (2025)
- [Military AI Cyber Agents (MAICAs) Constitute a Global Threat to Critical Infrastructure](https://mlsanity.com/paper/2506.12094/) (2025)
- [Managing Escalation in Off-the-Shelf Large Language Models](https://mlsanity.com/paper/2508.01056/) (2025)
- [Memory-Augmented State Machine Prompting: A Novel LLM Agent Framework for Real-Time Strategy Games](https://mlsanity.com/paper/2510.18395/) (2025)
- [Re-Envisioning Command and Control](https://mlsanity.com/paper/2402.07946/) (2024)
- [WARBENCH: A Comprehensive Benchmark for Evaluating LLMs in Military Decision-Making](https://mlsanity.com/paper/2603.21280/) (2026)
- [Controlled Territory and Conflict Tracking (CONTACT): (Geo-)Mapping Occupied Territory from Open Source Intelligence](https://mlsanity.com/paper/2504.13730/) (2025)
- [Towards AI-Assisted Generation of Military Training Scenarios](https://mlsanity.com/paper/2511.07690/) (2025)
- [Data Analysis and Performance Evaluation of Simulation Deduction Based on LLMs](https://mlsanity.com/paper/2511.10651/) (2025)
- [Architecture of an AI-Based Automated Course of Action Generation System for Military Operations](https://mlsanity.com/paper/2604.20862/) (2026)
- [MA-Bench: Measuring Operational Planning in Language Models](https://mlsanity.com/paper/2610.19138/) (2026)

## Abstract (arXiv)

The development of Courses of Action (COAs) in military operations is traditionally a time-consuming and intricate process. Addressing this challenge, this study introduces COA-GPT, a novel algorithm employing Large Language Models (LLMs) for rapid and efficient generation of valid COAs. COA-GPT incorporates military doctrine and domain expertise to LLMs through in-context learning, allowing commanders to input mission information - in both text and image formats - and receive strategically aligned COAs for review and approval. Uniquely, COA-GPT not only accelerates COA development, producing initial COAs within seconds, but also facilitates real-time refinement based on commander feedback. This work evaluates COA-GPT in a military-relevant scenario within a militarized version of the StarCraft II game, comparing its performance against state-of-the-art reinforcement learning algorithms. Our results demonstrate COA-GPT's superiority in generating strategically sound COAs more swiftly, with added benefits of enhanced adaptability and alignment with commander intentions. COA-GPT's capability to rapidly adapt and update COAs during missions presents a transformative potential for military planning, particularly in addressing planning discrepancies and capitalizing on emergent windows of opportunities.