{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:01:30Z","timestamp":1790787690093,"version":"4.1.0"},"reference-count":33,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"St. Petersburg Federal Research Center of the Russian Academy of Sciences under Grant Mol_Lab","award":["FFZF-2024-0003"],"award-info":[{"award-number":["FFZF-2024-0003"]}]},{"name":"Saint Petersburg Leonhard Euler International Mathematical Institute at the St. Petersburg Department of the V. A. Steklov Institute of Mathematics of the Russian Academy of Sciences","award":["075-15-2025-344"],"award-info":[{"award-number":["075-15-2025-344"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/access.2026.3710376","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T19:50:52Z","timestamp":1783367452000},"page":"116038-116061","source":"Crossref","is-referenced-by-count":1,"title":["MultiCAT-Bench: A Multi-Categorical Agent Tool Use Benchmark"],"prefix":"10.1109","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0376-8069","authenticated-orcid":false,"given":"Artyom","family":"Vyatkin","sequence":"first","affiliation":[{"name":"St. Petersburg Federal Research Center of the Russian Academy of Sciences","place":["St. Petersburg, Russia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2707-5659","authenticated-orcid":false,"given":"Aleksander","family":"Poptsov","sequence":"additional","affiliation":[{"name":"St. Petersburg Federal Research Center of the Russian Academy of Sciences","place":["St. Petersburg, Russia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3479-0085","authenticated-orcid":false,"given":"Valerii","family":"Oliseenko","sequence":"additional","affiliation":[{"name":"St. Petersburg Federal Research Center of the Russian Academy of Sciences","place":["St. Petersburg, Russia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1838-5629","authenticated-orcid":false,"given":"Evgeniya","family":"Veiber","sequence":"additional","affiliation":[{"name":"St. Petersburg Federal Research Center of the Russian Academy of Sciences","place":["St. Petersburg, Russia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8350-7000","authenticated-orcid":false,"given":"Oleg","family":"Shutko","sequence":"additional","affiliation":[{"name":"St. Petersburg Federal Research Center of the Russian Academy of Sciences","place":["St. Petersburg, Russia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9411-4888","authenticated-orcid":false,"given":"Timur","family":"Rafikov","sequence":"additional","affiliation":[{"name":"St. Petersburg Federal Research Center of the Russian Academy of Sciences","place":["St. Petersburg, Russia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5476-3025","authenticated-orcid":false,"given":"Maxim","family":"Abramov","sequence":"additional","affiliation":[{"name":"St. Petersburg Federal Research Center of the Russian Academy of Sciences","place":["St. Petersburg, Russia"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7787-2251","authenticated-orcid":false,"given":"Sergey I.","family":"Nikolenko","sequence":"additional","affiliation":[{"name":"Steklov Mathematical Institute","place":["St. Petersburg, Russia"],"department":["St. Petersburg Department"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"crossref","DOI":"10.1613\/jair.1.18675","article-title":"Agentic large language models, a survey","volume":"84","author":"Plaat","year":"2025","journal-title":"J. Artif. Intell. Res."},{"key":"ref2","article-title":"Proactive agent: Shifting LLM agents from reactive responses to active assistance","volume-title":"13th Int. Conf. Learn. Represent. (ICLR)","author":"Lu"},{"key":"ref3","article-title":"Agent-SafetyBench: Evaluating the safety of LLM agents","author":"Zhang","year":"2024","journal-title":"arXiv:2412.14470"},{"key":"ref4","article-title":"A survey of frontiers in LLM reasoning: Inference scaling, learning to reason, and agentic systems","author":"Ke","year":"2025","journal-title":"arXiv:2504.09037"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2026.findings-acl.1330"},{"key":"ref6","article-title":"Multi-IF: Benchmarking LLMs on multi-turn and multilingual instructions following","author":"He","year":"2024","journal-title":"arXiv:2410.15553"},{"key":"ref7","first-page":"48371","article-title":"The Berkeley function calling leaderboard (BFCL): From tool use to agentic evaluation of large language models","volume-title":"Proc. 42nd Int. Conf. Mach. Learn. (PMLR)","volume":"267","author":"Patil"},{"key":"ref8","first-page":"9510","article-title":"T-Eval: Evaluating the tool utilization capability of large language models step by step","volume-title":"Proc. 62nd Annu. Meeting Assoc. Comput. Linguistics","author":"Chen"},{"key":"ref9","article-title":"ShortcutsBench: A large-scale real-world benchmark for API-based agents","author":"Shen","year":"2024","journal-title":"arXiv:2407.00132"},{"key":"ref10","article-title":"NESTFUL: A benchmark for evaluating LLMs on nested sequences of API calls","author":"Basu","year":"2024","journal-title":"arXiv:2409.03797"},{"key":"ref11","article-title":"ComplexFuncBench: Exploring multi-step and constrained function calling under long-context scenario","author":"Zhong","year":"2025","journal-title":"arXiv:2501.10132"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"3350","DOI":"10.18653\/v1\/2025.findings-acl.175","article-title":"HammerBench: Fine-grained function-calling evaluation in real mobile assistant scenarios","volume-title":"Findings of the Association for Computational Linguistics: ACL 2025","author":"Wang","year":"2025"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.naacl-long.149"},{"key":"ref14","doi-asserted-by":"crossref","first-page":"12970","DOI":"10.18653\/v1\/2025.findings-emnlp.697","article-title":"ACEBench: A comprehensive evaluation of LLM tool usage","volume-title":"Findings of the Association for Computational Linguistics: EMNLP 2025","author":"Chen","year":"2025"},{"key":"ref15","article-title":"ToolACE: Winning the points of LLM function calling","author":"Liu","year":"2024","journal-title":"arXiv:2409.00920"},{"key":"ref16","first-page":"54463","article-title":"APIGen: Automated PIpeline for generating verifiable and diverse function-calling datasets","volume-title":"Proc. Adv. Neural Inf. Process. Syst","volume":"37","author":"Liu"},{"key":"ref17","volume-title":"Introducing the Model Context Protocol","year":"2024"},{"key":"ref18","article-title":"LiveMCPBench: Can agents navigate an ocean of MCP tools?","author":"Mo","year":"2025","journal-title":"arXiv:2508.01780"},{"key":"ref19","article-title":"MCPToolBench++: A large scale AI agent model context protocol MCP tool use benchmark","author":"Fan","year":"2025","journal-title":"arXiv:2508.07575"},{"key":"ref20","article-title":"MCP-RADAR: A multi-dimensional benchmark for evaluating tool use capabilities in large language models","author":"Gao","year":"2025","journal-title":"arXiv:2505.16700"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3736570"},{"key":"ref22","article-title":"MTU-Bench: A multi-granularity tool-use benchmark for large language models","author":"Wang","year":"2024","journal-title":"arXiv:2410.11710"},{"key":"ref23","article-title":"LongFuncEval: Measuring the effectiveness of long context models for function calling","author":"Kate","year":"2025","journal-title":"arXiv:2505.10570"},{"key":"ref24","volume-title":"GPT-5 System Card","year":"2025"},{"key":"ref25","volume-title":"Grok 4.1 Fast and Agent Tools API","year":"2025"},{"key":"ref26","volume-title":"GLM-4.7: Advancing the Coding Capability","year":"2025"},{"key":"ref27","volume-title":"Using Thinking Models, Kimi API Platform Documentation","year":"2025"},{"key":"ref28","volume-title":"Mistral Small 3.2 24b Instruct 2506 Model Card","year":"2025"},{"key":"ref29","volume-title":"MiniMax M2 & Agent: Ingenious in Simplicity","year":"2025"},{"key":"ref30","volume-title":"Qwen3-Next: Towards Ultimate Training & Inference Efficiency","year":"2025"},{"key":"ref31","volume-title":"Qwen3-Coder: Agentic Coding in the World","year":"2025"},{"key":"ref32","article-title":"DeepSeek-V3.2: Pushing the frontier of open large language models","author":"Liu","year":"2025","journal-title":"arXiv:2512.02556"},{"key":"ref33","volume-title":"Nemotron-3-Nano-30B-A3B Model Card","year":"2025"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/11323511\/11595574.pdf?arnumber=11595574","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,5]],"date-time":"2026-08-05T19:07:16Z","timestamp":1785956836000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11595574\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/access.2026.3710376","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}