Benchmark for Planning and Control with Large Language Model Agents: Blocksworld with Model Context Protocol

Fuente: arXiv
Enregistré dans:
Détails bibliographiques
Auteurs principaux: Jobs, Niklas, da Silva, Luis Miguel Vieira, Somashekaraiah, Jayanth, Weigand, Maximilian, Kube, David, Gehlhoff, Felix
Format: Preprint
Publié: 2025
Sujets:
Accès en ligne:
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866917122403205120
author Jobs, Niklas
da Silva, Luis Miguel Vieira
Somashekaraiah, Jayanth
Weigand, Maximilian
Kube, David
Gehlhoff, Felix
author_facet Jobs, Niklas
da Silva, Luis Miguel Vieira
Somashekaraiah, Jayanth
Weigand, Maximilian
Kube, David
Gehlhoff, Felix
contents Industrial automation increasingly requires flexible control strategies that can adapt to changing tasks and environments. Agents based on Large Language Models (LLMs) offer potential for such adaptive planning and execution but lack standardized benchmarks for systematic comparison. We introduce a benchmark with an executable simulation environment representing the Blocksworld problem providing five complexity categories. By integrating the Model Context Protocol (MCP) as a standardized tool interface, diverse agent architectures can be connected to and evaluated against the benchmark without implementation-specific modifications. A single-agent implementation demonstrates the benchmark's applicability, establishing quantitative metrics for comparison of LLM-based planning and execution approaches.
format Preprint
id arxiv_https___arxiv_org_abs_2512_03955
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Benchmark for Planning and Control with Large Language Model Agents: Blocksworld with Model Context Protocol
Jobs, Niklas
da Silva, Luis Miguel Vieira
Somashekaraiah, Jayanth
Weigand, Maximilian
Kube, David
Gehlhoff, Felix
Artificial Intelligence
Emerging Technologies
Industrial automation increasingly requires flexible control strategies that can adapt to changing tasks and environments. Agents based on Large Language Models (LLMs) offer potential for such adaptive planning and execution but lack standardized benchmarks for systematic comparison. We introduce a benchmark with an executable simulation environment representing the Blocksworld problem providing five complexity categories. By integrating the Model Context Protocol (MCP) as a standardized tool interface, diverse agent architectures can be connected to and evaluated against the benchmark without implementation-specific modifications. A single-agent implementation demonstrates the benchmark's applicability, establishing quantitative metrics for comparison of LLM-based planning and execution approaches.
title Benchmark for Planning and Control with Large Language Model Agents: Blocksworld with Model Context Protocol
topic Artificial Intelligence
Emerging Technologies
url https://arxiv.org/abs/2512.03955