Benchmark for Planning and Control with Large Language Model Agents: Blocksworld with Model Context Protocol
This provides a domain-specific benchmark for researchers and developers working on LLM agents in industrial automation, but it is incremental as it builds on existing Blocksworld and MCP concepts.
The authors tackled the lack of standardized benchmarks for LLM-based agents in planning and control by introducing a benchmark with an executable simulation environment for the Blocksworld problem, integrating the Model Context Protocol for tool interface standardization, and demonstrating its applicability with a single-agent implementation to establish quantitative metrics.
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.