GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866917799968899072 |
|---|---|
| author | Nasir, Muhammad Umair James, Steven Togelius, Julian |
| author_facet | Nasir, Muhammad Umair James, Steven Togelius, Julian |
| contents | Large language models (LLMs) have recently demonstrated great success in generating and understanding natural language. While they have also shown potential beyond the domain of natural language, it remains an open question as to what extent and in which way these LLMs can plan. We investigate their planning capabilities by proposing GameTraversalBenchmark (GTB), a benchmark consisting of diverse 2D grid-based game maps. An LLM succeeds if it can traverse through given objectives, with a minimum number of steps and a minimum number of generation errors. We evaluate a number of LLMs on GTB and found that GPT-4-Turbo achieved the highest score of 44.97% on GTB\_Score (GTBS), a composite score that combines the three above criteria. Furthermore, we preliminarily test large reasoning models, namely o1, which scores $67.84\%$ on GTBS, indicating that the benchmark remains challenging for current models. Code, data, and documentation are available at https://github.com/umair-nasir14/Game-Traversal-Benchmark. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2410_07765 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps Nasir, Muhammad Umair James, Steven Togelius, Julian Computation and Language Artificial Intelligence Large language models (LLMs) have recently demonstrated great success in generating and understanding natural language. While they have also shown potential beyond the domain of natural language, it remains an open question as to what extent and in which way these LLMs can plan. We investigate their planning capabilities by proposing GameTraversalBenchmark (GTB), a benchmark consisting of diverse 2D grid-based game maps. An LLM succeeds if it can traverse through given objectives, with a minimum number of steps and a minimum number of generation errors. We evaluate a number of LLMs on GTB and found that GPT-4-Turbo achieved the highest score of 44.97% on GTB\_Score (GTBS), a composite score that combines the three above criteria. Furthermore, we preliminarily test large reasoning models, namely o1, which scores $67.84\%$ on GTBS, indicating that the benchmark remains challenging for current models. Code, data, and documentation are available at https://github.com/umair-nasir14/Game-Traversal-Benchmark. |
| title | GameTraversalBenchmark: Evaluating Planning Abilities Of Large Language Models Through Traversing 2D Game Maps |
| topic | Computation and Language Artificial Intelligence |
| url | https://arxiv.org/abs/2410.07765 |