# From Gameplay Traces to Game Mechanics: Causal Induction with Large Language Models

arXiv: https://arxiv.org/abs/2602.00190 · HTML: https://mlsanity.com/paper/2602.00190/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 35 references that are in the map.
- First posted on arXiv 30 Jan 2026.

## Builds on (most cited first, 19 of 19)

- [Chain-of-Thought Prompting Elicits Reasoning in Large Language Models](https://mlsanity.com/paper/2201.11903/) (2022)
- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [QLoRA: Efficient Finetuning of Quantized LLMs](https://mlsanity.com/paper/2305.14314/) (2023)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [MiniLM: Deep Self-Attention Distillation for Task-Agnostic Compression of Pre-Trained Transformers](https://mlsanity.com/paper/2002.10957/) (2020)
- [Logic-LM: Empowering Large Language Models with Symbolic Solvers for Faithful Logical Reasoning](https://mlsanity.com/paper/2305.12295/) (2023)
- [Task Contamination: Language Models May Not Be Few-Shot Anymore](https://mlsanity.com/paper/2312.16337/) (2023)
- [Game Generation via Large Language Models](https://mlsanity.com/paper/2404.08706/) (2024)
- [GAVEL: Generating Games Via Evolution and Language Models](https://mlsanity.com/paper/2407.09388/) (2024)
- [Causal Reinforcement Learning: A Survey](https://mlsanity.com/paper/2307.01452/) (2023)
- [Reasoning about Causality in Games](https://mlsanity.com/paper/2301.02324/) (2023)
- [AlphaStar Unplugged: Large-Scale Offline Reinforcement Learning](https://mlsanity.com/paper/2308.03526/) (2023)
- [Investigating Symbolic Capabilities of Large Language Models](https://mlsanity.com/paper/2405.13209/) (2024)
- [From Chess and Atari to StarCraft and Beyond: How Game AI is Driving the World of AI](https://mlsanity.com/paper/2002.10433/) (2020)
- [Grammar-based Game Description Generation using Large Language Models](https://mlsanity.com/paper/2407.17404/) (2024)
- [Frugal LMs Trained to Invoke Symbolic Solvers Achieve Parameter-Efficient Arithmetic Reasoning](https://mlsanity.com/paper/2312.05571/) (2023)
- [Causality-Based Game Solving](https://mlsanity.com/paper/2105.14247/) (2021)
- [Grammar and Gameplay-aligned RL for Game Description Generation with LLMs](https://mlsanity.com/paper/2503.15783/) (2025)
- [Rule Synergy Analysis using LLMs: State of the Art and Implications](https://mlsanity.com/paper/2508.19484/) (2025)

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

- [Spatial Reasoning in LLM Game Agents: Impact of Causal Context and Multi-Step Planning](https://mlsanity.com/paper/2607.22732/) (2026)
- [Compiling VGDL into Causal Models](https://mlsanity.com/paper/2609.05459/) (2026)

## Abstract (arXiv)

Deep learning agents can achieve high performance in complex game domains without often understanding the underlying causal game mechanics. To address this, we investigate Causal Induction: the ability to infer governing laws from observational data, by tasking Large Language Models (LLMs) with reverse-engineering Video Game Description Language (VGDL) rules from gameplay traces. To reduce redundancy, we select nine representative games from the General Video Game AI (GVGAI) framework using semantic embeddings and clustering. We compare two approaches to VGDL generation: direct code generation from observations, and a two-stage method that first infers a structural causal model (SCM) and then translates it into VGDL. Both approaches are evaluated across multiple prompting strategies and controlled context regimes, varying the amount and form of information provided to the model, from just raw gameplay observations to partial VGDL specifications. Results show that the SCM-based approach more often produces VGDL descriptions closer to the ground truth than direct generation, achieving preference win rates of up to 81% in blind evaluations and yielding fewer logically inconsistent rules. These learned SCMs can be used for downstream use cases such as causal reinforcement learning, interpretable agents, and procedurally generating novel but logically consistent games.