# Playing NetHack with LLMs: Potential & Limitations as Zero-Shot Agents

arXiv: https://arxiv.org/abs/2403.00690 · HTML: https://mlsanity.com/paper/2403.00690/

## Key facts

- Cited by 17 papers in the map (data through 14 Oct 2026).
- Placed in Reinforcement learning for LLM agents, one of 16 directions in LLM agents and tool use.
- Builds on 16 of its 20 references that are in the map.
- First posted on arXiv 1 Mar 2024.

## Placed in

- LLM agents and tool use / [Reinforcement learning for LLM agents](https://mlsanity.com/agents/reinforcement-learning-for-llm-agents/)

## Builds on (most cited first, 16 of 16)

- [Llama 2: Open Foundation and Fine-Tuned Chat Models](https://mlsanity.com/paper/2307.09288/) (2023)
- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [Code as Policies: Language Model Programs for Embodied Control](https://mlsanity.com/paper/2209.07753/) (2022)
- [Inner Monologue: Embodied Reasoning through Planning with Language Models](https://mlsanity.com/paper/2207.05608/) (2022)
- [A Comprehensive Overview of Large Language Models](https://mlsanity.com/paper/2307.06435/) (2023)
- [Eureka: Human-Level Reward Design via Coding Large Language Models](https://mlsanity.com/paper/2310.12931/) (2023)
- [LLM-Planner: Few-Shot Grounded Planning for Embodied Agents with Large Language Models](https://mlsanity.com/paper/2212.04088/) (2022)
- [Describe, Explain, Plan and Select: Interactive Planning with Large Language Models Enables Open-World Multi-Task Agents](https://mlsanity.com/paper/2302.01560/) (2023)
- [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)
- [Reward Design with Language Models](https://mlsanity.com/paper/2303.00001/) (2023)
- [The NetHack Learning Environment](https://mlsanity.com/paper/2006.13760/) (2020)
- [JARVIS-1: Open-World Multi-task Agents with Memory-Augmented Multimodal Language Models](https://mlsanity.com/paper/2311.05997/) (2023)
- [Motif: Intrinsic Motivation from Artificial Intelligence Feedback](https://mlsanity.com/paper/2310.00166/) (2023)
- [MiniHack the Planet: A Sandbox for Open-Ended Reinforcement Learning Research](https://mlsanity.com/paper/2109.13202/) (2021)
- [Insights From the NeurIPS 2021 NetHack Challenge](https://mlsanity.com/paper/2203.11889/) (2022)

## Built on by (most cited first, 17 of 17)

- [BALROG: Benchmarking Agentic LLM and VLM Reasoning On Games](https://mlsanity.com/paper/2411.13543/) (2024)
- [A Survey on Large Language Model-Based Game Agents](https://mlsanity.com/paper/2404.02039/) (2024)
- [AriGraph: Learning Knowledge Graph World Models with Episodic Memory for LLM Agents](https://mlsanity.com/paper/2407.04363/) (2024)
- [A Survey of Agentic Reasoning for Large Language Models: Towards Recursively Self-Improving and Collective Agents](https://mlsanity.com/paper/2601.12538/) (2026)
- [LLM Economist: Large Population Models and Mechanism Design in Multi-Agent Generative Simulacra](https://mlsanity.com/paper/2507.15815/) (2025)
- [Pok'eChamp: an Expert-level Minimax Language Agent](https://mlsanity.com/paper/2503.04094/) (2025)
- [MLLM as Retriever: Interactively Learning Multimodal Retrieval for Embodied Agents](https://mlsanity.com/paper/2410.03450/) (2024)
- [Online Intrinsic Rewards for Decision Making Agents from Large Language Model Feedback](https://mlsanity.com/paper/2410.23022/) (2024)
- [GPT for Games: An Updated Scoping Review (2020-2024)](https://mlsanity.com/paper/2411.00308/) (2024)
- [Codenames as a Benchmark for Large Language Models](https://mlsanity.com/paper/2412.11373/) (2024)
- [Learning Game-Playing Agents with Generative Code Optimization](https://mlsanity.com/paper/2508.19506/) (2025)
- [Assessing the Zero-Shot Capabilities of LLMs for Action Evaluation in RL](https://mlsanity.com/paper/2409.12798/) (2024)
- [Leveraging LLM Agents for Automated Video Game Testing](https://mlsanity.com/paper/2509.22170/) (2025)
- [AutoMem: Automated Learning of Memory as a Cognitive Skill](https://mlsanity.com/paper/2607.01224/) (2026)
- [MINDSTORES: Memory-Informed Neural Decision Synthesis for Task-Oriented Reinforcement in Embodied Systems](https://mlsanity.com/paper/2501.19318/) (2025)
- [Code Driven Planning with Domain-Adaptive Critic](https://mlsanity.com/paper/2509.19077/) (2025)
- [Up and Down the Abstraction Ladder: Code-Based Skills for Language Agents](https://mlsanity.com/paper/2609.31076/) (2026)

## Abstract (arXiv)

Large Language Models (LLMs) have shown great success as high-level planners for zero-shot game-playing agents. However, these agents are primarily evaluated on Minecraft, where long-term planning is relatively straightforward. In contrast, agents tested in dynamic robot environments face limitations due to simplistic environments with only a few objects and interactions. To fill this gap in the literature, we present NetPlay, the first LLM-powered zero-shot agent for the challenging roguelike NetHack. NetHack is a particularly challenging environment due to its diverse set of items and monsters, complex interactions, and many ways to die. NetPlay uses an architecture designed for dynamic robot environments, modified for NetHack. Like previous approaches, it prompts the LLM to choose from predefined skills and tracks past interactions to enhance decision-making. Given NetHack's unpredictable nature, NetPlay detects important game events to interrupt running skills, enabling it to react to unforeseen circumstances. While NetPlay demonstrates considerable flexibility and proficiency in interacting with NetHack's mechanics, it struggles with ambiguous task descriptions and a lack of explicit feedback. Our findings demonstrate that NetPlay performs best with detailed context information, indicating the necessity for dynamic methods in supplying context information for complex games such as NetHack.