{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:15:19Z","timestamp":1774419319535,"version":"3.50.1"},"reference-count":32,"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"}],"funder":[{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889153","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:02Z","timestamp":1741799702000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["WTU-EVAL: A Whether-or-Not Tool Usage Evaluation Benchmark for Large Language Models"],"prefix":"10.1109","author":[{"given":"Jian","family":"Liu","sequence":"first","affiliation":[{"name":"University of Science and Technology,Beijing"}]},{"given":"Kangyun","family":"Ning","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China"}]},{"given":"Yisong","family":"Su","sequence":"additional","affiliation":[{"name":"Fuzhou University,College of Computer and Data Science,Fuzhou,China"}]},{"given":"Wenjuan","family":"Han","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China"}]},{"given":"Jinan","family":"Xu","sequence":"additional","affiliation":[{"name":"Beijing Jiaotong University,Beijing Key Lab of Traffic Data Analysis and Mining,Beijing,China"}]},{"given":"Yuanzhe","family":"Zhang","sequence":"additional","affiliation":[{"name":"Chinese Academy of Sciences,National Science Library,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3704435"},{"key":"ref2","article-title":"Toolllm: Facilitating large language models to master 16000+ real-world apis","author":"Qin","year":"2023"},{"key":"ref3","article-title":"ToolQA: A dataset for LLM question answering with external tools","author":"Zhuang","year":"2023"},{"key":"ref4","article-title":"Metatool benchmark for large language models: Deciding whether to use tools and which to use","author":"Huang","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.926"},{"key":"ref6","article-title":"Mint: Evaluating LLMs in multi-turn interaction with tools and language feedback","author":"Wang","year":"2023"},{"key":"ref7","article-title":"ToolEyes: Fine-grained evaluation for tool learning capabilities of large language models in real-world scenarios","author":"Ye","year":"2024"},{"key":"ref8","article-title":"Training verifiers to solve math word problems","author":"Cobbe","year":"2021"},{"key":"ref9","article-title":"Mathqa: Towards interpretable math word problem solving with operation-based formalisms","author":"Amini","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.653"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1259"},{"key":"ref12","article-title":"RealTime QA: What\u2019s the answer right now?","author":"Kasai","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.92"},{"key":"ref14","article-title":"BoolQ: Exploring the surprising difficulty of natural yes\/no questions","author":"Clark","year":"2019"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1082"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6239"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1472"},{"key":"ref18","article-title":"React: Synergizing reasoning and acting in language models","author":"Yao","year":"2022"},{"key":"ref19","article-title":"Gorilla: Large language model connected with massive apis","author":"Patil","year":"2023"},{"key":"ref20","article-title":"Tptu: Task planning and tool usage of large language model-based ai agents","author":"Ruan","year":"2023"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/11736790_9"},{"key":"ref22","article-title":"Llama 2: Open foundation and fine-tuned chat models, 2023","author":"Touvron","year":"2023"},{"key":"ref23","article-title":"ToolAlpaca: Generalized tool learning for language models with 3000 simulated cases","author":"Tang","year":"2023"},{"key":"ref24","article-title":"Mind2Web: Towards a generalist agent for the web","author":"Deng","year":"2023"},{"key":"ref25","article-title":"Zephyr: Direct distillation of LM alignment","author":"Tunstall","year":"2023"},{"key":"ref26","article-title":"GPT-4 technical report","year":"2023"},{"key":"ref27","article-title":"Tool-augmented reward modeling","author":"Li","year":"2023"},{"key":"ref28","article-title":"Toolchain*: Efficient action space navigation in large language models with a* search","author":"Zhuang","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.378"},{"key":"ref30","article-title":"Demonstrate-search-predict: Composing retrieval and language models for knowledge-intensive NLP","author":"Khattab","year":"2022"},{"key":"ref31","article-title":"Toolformer: Language models can teach themselves to use tools","author":"Schick","year":"2023"},{"key":"ref32","article-title":"ART: Automatic multi-step reasoning and tool-use for large language models","author":"Paranjape","year":"2023"}],"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\/10889153.pdf?arnumber=10889153","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:22:15Z","timestamp":1774416135000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889153\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889153","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}