ShortcutsBench: A Large-Scale Real-world Benchmark for API-based Agents
Keywords: Benchmark, Agent, LLM, Shortcuts
Abstract: Recent advancements in integrating large language models (LLMs) with application programming interfaces (APIs) have gained significant interest in both academia and industry. Recent work demonstrates that these API-based agents exhibit relatively strong autonomy and planning capabilities. However, their ability to handle multi-dimensional difficulty levels, diverse task types, and real-world demands remains unknown.
In this paper, we introduce ShortcutsBench, a large-scale benchmark for the comprehensive evaluation of API-based agents in solving real-world complex tasks. ShortcutsBench includes a wealth of real APIs from Apple Inc., refined user queries, human-annotated
high-quality action sequences, detailed parameter filling values, and parameters requesting necessary input from the system or user. We put in significant effort in collecting and processing the data. We revealed how existing benchmarks / datasets struggle to accommodate the advanced reasoning capabilities of existing more intelligent LLMs. Moreover, our extensive evaluation of agents built with 5 leading open-source (size >= 57B) and 5 closed-source LLMs (e.g. Gemini-1.5-Pro and GPT-4o-mini) reveals significant limitations of existing API-based agents in the whole process of handling complex queries related to API selection, parameter filling, and requesting necessary input from the system and the user. These findings highlight the great challenges that API-based agents face in effectively fulfilling real and complex user queries. All datasets, code, experimental logs, and results are available at \url{https://anonymous.4open.science/r/ShortcutsBench}.
Primary Area: datasets and benchmarks
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2025/AuthorGuide.
Reciprocal Reviewing: I understand the reciprocal reviewing requirement as described on https://iclr.cc/Conferences/2025/CallForPapers. If none of the authors are registered as a reviewer, it may result in a desk rejection at the discretion of the program chairs. To request an exception, please complete this form at https://forms.gle/Huojr6VjkFxiQsUp6.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors’ identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Submission Number: 880
Loading