Auto-SLURP: A Benchmark Dataset for Evaluating Multi-Agent Frameworks in Smart Personal Assistant

2025-04-25

AI Summary

Existing research lacks a dedicated benchmark for evaluating multi-agent frameworks in intelligent personal assistant scenarios. Method: We introduce Auto-SLURP, the first task-oriented benchmark specifically designed for this purpose. It re-annotates the SLURP dataset with executable task specifications, and integrates a reproducible execution environment with simulated external services to enable end-to-end evaluation of language understanding, task planning, tool invocation, and response generation. Contribution/Results: Auto-SLURP pioneers the transformation of traditional NLU datasets into a multi-agent system evaluation platform, overcoming the limitations of static intent classification. Empirical evaluation reveals that state-of-the-art multi-agent frameworks exhibit significant deficiencies in reliability and inter-agent coordination—particularly on long-horizon tasks. To foster community advancement, we open-source the benchmark data, implementation code, and standardized evaluation pipeline, establishing a foundational infrastructure for rigorous, comparable assessment of multi-agent assistants.

Technology Category

• Multiagent Systems: Multiagent Planning
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Multi-Robot Systems

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

In recent years, multi-agent frameworks powered by large language models (LLMs) have advanced rapidly. Despite this progress, there is still a notable absence of benchmark datasets specifically tailored to evaluate their performance. To bridge this gap, we introduce Auto-SLURP, a benchmark dataset aimed at evaluating LLM-based multi-agent frameworks in the context of intelligent personal assistants. Auto-SLURP extends the original SLURP dataset -- initially developed for natural language understanding tasks -- by relabeling the data and integrating simulated servers and external services. This enhancement enables a comprehensive end-to-end evaluation pipeline, covering language understanding, task execution, and response generation. Our experiments demonstrate that Auto-SLURP presents a significant challenge for current state-of-the-art frameworks, highlighting that truly reliable and intelligent multi-agent personal assistants remain a work in progress. The dataset and related code are available at https://github.com/lorashen/Auto-SLURP/.

Problem

• Lacks benchmark datasets for multi-agent framework evaluation
• Needs comprehensive evaluation of LLM-based personal assistants
• Requires end-to-end testing of language understanding and task execution

Innovation

• Extends SLURP dataset for multi-agent evaluation
• Integrates simulated servers and external services
• Enables end-to-end evaluation pipeline