A LLM Benchmark based on the Minecraft Builder Dialog Agent Task

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Madge, Chris, Poesio, Massimo
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914875130773504
author Madge, Chris
Poesio, Massimo
author_facet Madge, Chris
Poesio, Massimo
contents In this work we proposing adapting the Minecraft builder task into an LLM benchmark suitable for evaluating LLM ability in spatially orientated tasks, and informing builder agent design. Previous works have proposed corpora with varying complex structures, and human written instructions. We instead attempt to provide a comprehensive synthetic benchmark for testing builder agents over a series of distinct tasks that comprise of common building operations. We believe this approach allows us to probe specific strengths and weaknesses of different agents, and test the ability of LLMs in the challenging area of spatial reasoning and vector based math.
format Preprint
id arxiv_https___arxiv_org_abs_2407_12734
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A LLM Benchmark based on the Minecraft Builder Dialog Agent Task
Madge, Chris
Poesio, Massimo
Computation and Language
In this work we proposing adapting the Minecraft builder task into an LLM benchmark suitable for evaluating LLM ability in spatially orientated tasks, and informing builder agent design. Previous works have proposed corpora with varying complex structures, and human written instructions. We instead attempt to provide a comprehensive synthetic benchmark for testing builder agents over a series of distinct tasks that comprise of common building operations. We believe this approach allows us to probe specific strengths and weaknesses of different agents, and test the ability of LLMs in the challenging area of spatial reasoning and vector based math.
title A LLM Benchmark based on the Minecraft Builder Dialog Agent Task
topic Computation and Language
url https://arxiv.org/abs/2407.12734