# SPRING: Studying the Paper and Reasoning to Play Games

arXiv: https://arxiv.org/abs/2305.15486 · HTML: https://mlsanity.com/paper/2305.15486/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning for agents, planning and code, one of 17 directions in LLM reasoning.
- Builds on 33 of its 54 references that are in the map.
- First posted on arXiv 24 May 2023.

## Placed in

- LLM reasoning / [Reasoning for agents, planning and code](https://mlsanity.com/lr/reasoning-for-agents-planning-and-code/)

## Builds on (most cited first, 30 of 33)

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [PaLM: Scaling Language Modeling with Pathways](https://mlsanity.com/paper/2204.02311/) (2022)
- [Large Language Models are Zero-Shot Reasoners](https://mlsanity.com/paper/2205.11916/) (2022)
- [Reflexion: Language Agents with Verbal Reinforcement Learning](https://mlsanity.com/paper/2303.11366/) (2023)
- [Finetuned Language Models Are Zero-Shot Learners](https://mlsanity.com/paper/2109.01652/) (2021)
- [Self-Refine: Iterative Refinement with Self-Feedback](https://mlsanity.com/paper/2303.17651/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Sparks of Artificial General Intelligence: Early experiments with GPT-4](https://mlsanity.com/paper/2303.12712/) (2023)
- [Do As I Can, Not As I Say: Grounding Language in Robotic Affordances](https://mlsanity.com/paper/2204.01691/) (2022)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [D4RL: Datasets for Deep Data-Driven Reinforcement Learning](https://mlsanity.com/paper/2004.07219/) (2020)
- [Mastering Diverse Domains through World Models](https://mlsanity.com/paper/2301.04104/) (2023)
- [ALFWorld: Aligning Text and Embodied Environments for Interactive Learning](https://mlsanity.com/paper/2010.03768/) (2020)
- [Mastering Atari with Discrete World Models](https://mlsanity.com/paper/2010.02193/) (2020)
- [Exploration by Random Network Distillation](https://mlsanity.com/paper/1810.12894/) (2018)
- [Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model](https://mlsanity.com/paper/2201.11990/) (2022)
- [Segment Everything Everywhere All at Once](https://mlsanity.com/paper/2304.06718/) (2023)
- [MineDojo: Building Open-Ended Embodied Agents with Internet-Scale Knowledge](https://mlsanity.com/paper/2206.08853/) (2022)
- [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)
- [Benchmarking the Spectrum of Agent Capabilities](https://mlsanity.com/paper/2109.06780/) (2021)
- [Guiding Pretraining in Reinforcement Learning with Large Language Models](https://mlsanity.com/paper/2302.06692/) (2023)
- [Using Natural Language for Reward Shaping in Reinforcement Learning](https://mlsanity.com/paper/1903.02020/) (2019)
- [Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning](https://mlsanity.com/paper/1712.07294/) (2017)
- [Grounding Language to Entities and Dynamics for Generalization in Reinforcement Learning](https://mlsanity.com/paper/2101.07393/) (2021)
- [Read and Reap the Rewards: Learning to Play Atari with the Help of Instruction Manuals](https://mlsanity.com/paper/2302.04449/) (2023)
- [The MineRL 2020 Competition on Sample Efficient Reinforcement Learning using Human Priors](https://mlsanity.com/paper/2101.11071/) (2021)
- [General-Purpose Question-Answering with Macaw](https://mlsanity.com/paper/2109.02593/) (2021)
- [Skill Reinforcement Learning and Planning for Open-World Long-Horizon Tasks](https://mlsanity.com/paper/2303.16563/) (2023)

## Built on by (most cited first, 11 of 11)

- [Promptbreeder: Self-Referential Self-Improvement Via Prompt Evolution](https://mlsanity.com/paper/2309.16797/) (2023)
- [Large Language Models Play StarCraft II: Benchmarks and A Chain of Summarization Approach](https://mlsanity.com/paper/2312.11865/) (2023)
- [EnvGen: Generating and Adapting Environments via LLMs for Training Embodied Agents](https://mlsanity.com/paper/2403.12014/) (2024)
- [Assessing Logical Puzzle Solving in Large Language Models: Insights from a Minesweeper Case Study](https://mlsanity.com/paper/2311.07387/) (2023)
- [EMemBench: Interactive Benchmarking of Episodic Memory for VLM Agents](https://mlsanity.com/paper/2601.16690/) (2026)
- [Improving Sample Efficiency of Reinforcement Learning with Background Knowledge from Large Language Models](https://mlsanity.com/paper/2407.03964/) (2024)
- [Potential Benefits of Employing Large Language Models in Research in Moral Education and Development](https://mlsanity.com/paper/2306.13805/) (2023)
- [AI for Games in the Foundation Model Era](https://mlsanity.com/paper/2609.16679/) (2026)
- [Sensi: Learn One Thing at a Time -- Curriculum-Based Test-Time Learning for LLM Game Agents](https://mlsanity.com/paper/2603.17683/) (2026)
- [Nemobot Games: Crafting Strategic AI Gaming Agents for Interactive Learning with Large Language Models](https://mlsanity.com/paper/2604.21896/) (2026)
- [GlyphBench: A Playground for Language-Model Reinforcement Learning](https://mlsanity.com/paper/2609.34214/) (2026)

## Abstract (arXiv)

Open-world survival games pose significant challenges for AI algorithms due to their multi-tasking, deep exploration, and goal prioritization requirements. Despite reinforcement learning (RL) being popular for solving games, its high sample complexity limits its effectiveness in complex open-world games like Crafter or Minecraft. We propose a novel approach, SPRING, to read the game's original academic paper and use the knowledge learned to reason and play the game through a large language model (LLM). Prompted with the LaTeX source as game context and a description of the agent's current observation, our SPRING framework employs a directed acyclic graph (DAG) with game-related questions as nodes and dependencies as edges. We identify the optimal action to take in the environment by traversing the DAG and calculating LLM responses for each node in topological order, with the LLM's answer to final node directly translating to environment actions. In our experiments, we study the quality of in-context "reasoning" induced by different forms of prompts under the setting of the Crafter open-world environment. Our experiments suggest that LLMs, when prompted with consistent chain-of-thought, have great potential in completing sophisticated high-level trajectories. Quantitatively, SPRING with GPT-4 outperforms all state-of-the-art RL baselines, trained for 1M steps, without any training. Finally, we show the potential of games as a test bed for LLMs.