{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:07:59Z","timestamp":1776888479499,"version":"3.51.2"},"reference-count":26,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890828","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":1,"title":["Tool Playgrounds: A Comprehensive and Analyzable Benchmark for LLM Tool Invocation"],"prefix":"10.1109","author":[{"given":"Zhiwei","family":"Dong","sequence":"first","affiliation":[{"name":"University of Science and Technology,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruihao","family":"Gong","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Yong","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuo","family":"Wu","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongqiang","family":"Yao","sequence":"additional","affiliation":[{"name":"SenseTime Research"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song-Lu","family":"Chen","sequence":"additional","affiliation":[{"name":"University of Science and Technology,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xu-Cheng","family":"Yin","sequence":"additional","affiliation":[{"name":"University of Science and Technology,Beijing"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref2","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"issue":"8","key":"ref3","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref4","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"issue":"140","key":"ref5","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of Machine Learning Research"},{"key":"ref6","article-title":"Xlnet: Generalized autoregressive pretraining for language understanding","volume":"32","author":"Yang","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref7","article-title":"The claude 3 model family: Opus, sonnet, haiku","author":"Anthropic","year":"2024","journal-title":"Claude-3 Model Card"},{"key":"ref8","article-title":"Command r","year":"2024"},{"key":"ref9","article-title":"Gorilla: Large language model connected with massive apis","author":"Patil","year":"2023"},{"key":"ref10","article-title":"Toolllm: Facilitating large language models to master 16000+ real-world apis","author":"Qin","year":"2023"},{"key":"ref11","article-title":"Chatgpt: Optimizing language models for dialogue","year":"2024"},{"key":"ref12","article-title":"Nexusraven: Surpassing the state-of-the-art in open-source function calling llms","author":"team","year":"2023"},{"key":"ref13","article-title":"Toolalpaca: Generalized tool learning for language models with 3000 simulated cases","author":"Tang","year":"2023"},{"key":"ref14","article-title":"Berkeley function calling leaderboard","author":"Yan","year":"2024"},{"key":"ref15","article-title":"Gameeval: Evaluating llms on conversational games","author":"Qiao","year":"2023"},{"key":"ref16","article-title":"Smartplay: A benchmark for llms as intelligent agents","author":"Wu","year":"2023"},{"key":"ref17","article-title":"Infiagent-dabench: Evaluating agents on data analysis tasks","author":"Hu","year":"2024"},{"key":"ref18","article-title":"Travelplanner: A benchmark for real-world planning with language agents","author":"Xie","year":"2024"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-naacl.65"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.624"},{"key":"ref21","article-title":"T-eval: Evaluating the tool utilization capability step by step","author":"Chen","year":"2023"},{"key":"ref22","article-title":"Tooleyes: Fine-grained evaluation for tool learning capabilities of large language models in real-world scenarios","author":"Ye","year":"2024"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29777"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.187"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72684-2_2"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.664"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10890828.pdf?arnumber=10890828","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:35Z","timestamp":1774416155000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890828\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":26,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890828","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}