ParaCook: On Time-Efficient Planning for Multi-Agent Systems

2025-10-13

AI Summary

Existing multi-agent benchmarks largely overlook temporal efficiency under parallel and asynchronous execution. This paper introduces ParaCook—the first benchmark explicitly designed for time-efficient collaborative planning—inspired by Overcooked but featuring a simplified action space and tunable task complexity to enable faithful modeling of asynchronous and parallel operations. Methodologically, it leverages large language models (LLMs) for high-level, temporally aware reasoning, shifting focus from low-level action execution to time-optimized coordination strategies. Experimental results reveal significant bottlenecks in current LLMs’ ability to manage parallel coordination and dynamic resource allocation; however, they demonstrate feasibility of temporal reasoning at the abstract policy level. ParaCook provides a scalable, reproducible, and standardized evaluation platform for advancing time-sensitive multi-agent systems, enabling rigorous assessment of temporal efficiency in collaborative planning.

Technology Category

• Multiagent Systems: Multiagent Planning
• Planning, Routing, and Scheduling: Temporal Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG

Abstract

Large Language Models (LLMs) exhibit strong reasoning abilities for planning long-horizon, real-world tasks, yet existing agent benchmarks focus on task completion while neglecting time efficiency in parallel and asynchronous operations. To address this, we present ParaCook, a benchmark for time-efficient collaborative planning. Inspired by the Overcooked game, ParaCook provides an environment for various challenging interaction planning of multi-agent systems that are instantiated as cooking tasks, with a simplified action space to isolate the core challenge of strategic parallel planning. Through a comprehensive evaluation of state-of-the-art LLMs, we find that current approaches achieve suboptimal plans, which struggle with parallel actions or coordination. Our analysis also reveals LLMs' potential on abstract tasks where they can focus on high-level parallel optimization. ParaCook provides a scalable evaluation framework with adjustable complexity, establishing a foundation for developing and assessing time efficiency-aware multi-agent planning. The code and data are available at https://github.com/zsq259/ParaCook.

Problem

• Evaluating time-efficient planning in multi-agent systems
• Addressing suboptimal parallel action coordination in LLMs
• Providing scalable benchmark for strategic parallel planning

Innovation

• ParaCook benchmark for time-efficient multi-agent planning
• Simplified action space to isolate parallel planning challenges
• Scalable evaluation framework with adjustable complexity levels