PLANET: A Collection of Benchmarks for Evaluating LLMs' Planning Capabilities

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Li, Haoming, Chen, Zhaoliang, Zhang, Jonathan, Liu, Fei
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915251661832192
author Li, Haoming
Chen, Zhaoliang
Zhang, Jonathan
Liu, Fei
author_facet Li, Haoming
Chen, Zhaoliang
Zhang, Jonathan
Liu, Fei
contents Planning is central to agents and agentic AI. The ability to plan, e.g., creating travel itineraries within a budget, holds immense potential in both scientific and commercial contexts. Moreover, optimal plans tend to require fewer resources compared to ad-hoc methods. To date, a comprehensive understanding of existing planning benchmarks appears to be lacking. Without it, comparing planning algorithms' performance across domains or selecting suitable algorithms for new scenarios remains challenging. In this paper, we examine a range of planning benchmarks to identify commonly used testbeds for algorithm development and highlight potential gaps. These benchmarks are categorized into embodied environments, web navigation, scheduling, games and puzzles, and everyday task automation. Our study recommends the most appropriate benchmarks for various algorithms and offers insights to guide future benchmark development.
format Preprint
id arxiv_https___arxiv_org_abs_2504_14773
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle PLANET: A Collection of Benchmarks for Evaluating LLMs' Planning Capabilities
Li, Haoming
Chen, Zhaoliang
Zhang, Jonathan
Liu, Fei
Artificial Intelligence
Computation and Language
Machine Learning
Multiagent Systems
Planning is central to agents and agentic AI. The ability to plan, e.g., creating travel itineraries within a budget, holds immense potential in both scientific and commercial contexts. Moreover, optimal plans tend to require fewer resources compared to ad-hoc methods. To date, a comprehensive understanding of existing planning benchmarks appears to be lacking. Without it, comparing planning algorithms' performance across domains or selecting suitable algorithms for new scenarios remains challenging. In this paper, we examine a range of planning benchmarks to identify commonly used testbeds for algorithm development and highlight potential gaps. These benchmarks are categorized into embodied environments, web navigation, scheduling, games and puzzles, and everyday task automation. Our study recommends the most appropriate benchmarks for various algorithms and offers insights to guide future benchmark development.
title PLANET: A Collection of Benchmarks for Evaluating LLMs' Planning Capabilities
topic Artificial Intelligence
Computation and Language
Machine Learning
Multiagent Systems
url https://arxiv.org/abs/2504.14773