HammerBench: Fine-Grained Function-Calling Evaluation in Real Mobile Device Scenarios

TL;DR

HammerBench is a comprehensive benchmark framework designed to evaluate large language models' function-calling abilities in realistic multi-turn mobile assistant scenarios, addressing the complexity of user interactions and external information use.

Contribution

We introduce HammerBench, a new benchmark with detailed metrics and datasets for assessing LLMs' function-calling in real-world mobile assistant dialogues, including diverse interaction challenges.

Findings

Different parameter name errors significantly impact performance.

Performance varies across interaction scenarios, highlighting robustness issues.

HammerBench effectively reveals key failure modes in LLM function calling.

Abstract

Evaluating the performance of LLMs in multi-turn human-agent interactions presents significant challenges, particularly due to the complexity and variability of user behavior. In this paper, we introduce HammerBench, a novel benchmark framework for assessing LLMs' function-calling capabilities in real-world, multi-turn dialogues. HammerBench simulates diverse mobile assistant use cases, incorporating imperfect instructions, dynamic question-answer trajectories, intent and argument shifts, and the indirect use of external information through pronouns. To construct this benchmark, we curate a comprehensive dataset derived from popular mobile app functionalities and anonymized user logs, complemented by a cost-effective data generation pipeline leveraging open-source models. HammerBench is further augmented with fine-grained interaction snapshots and metrics, enabling detailed evaluation of function-calling performance across individual conversational turns. We demonstrate the effectiveness of HammerBench by evaluating several leading LLMs and uncovering key performance trends. Our experiments reveal that different types of parameter name errors are a significant source of failure across different interaction scenarios, highlighting critical areas for further improvement in LLM robustness for mobile assistant applications.