---
title: "MCP-Flow — paper by Wang et al. (2026) — summary and ideas"
description: "LLM agents increasingly need to work with tools exposed through the Model Contextual Protocol… 46 references, cited by 7 papers here."
authors: ["WenHao Wang", "Peizhi Niu", "Zhao Xu", "Zhaoyu Chen", "Jian Du", "Yaxin Du", "Xianghe Pang", "Keduan Huang", "Yanfeng Wang", "Qiang Yan", "Siheng Chen"]
year: 2026
venue: "Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)"
source: "https://aclanthology.org/2026.acl-long.231/"
doi: "10.18653/v1/2026.acl-long.231"
licence: "CC BY 4.0 (ACL Anthology)"
licence_url: "https://creativecommons.org/licenses/by/4.0/"
summary_licence: "Elamur Cosmic License"
canonical: "https://research.elamur.ai/free/en/papers/wang-2026-mcp-flow-facilitating-llm-agents/"
---
[Elamur Research](https://md.research.elamur.ai/free/en/) · [this page in HTML](https://research.elamur.ai/free/en/papers/wang-2026-mcp-flow-facilitating-llm-agents/)

[home](https://md.research.elamur.ai/free/en/) / [papers](https://md.research.elamur.ai/free/en/papers/) / [2026](https://md.research.elamur.ai/free/en/papers/2026/page/2/) / MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools

# MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools

**Authors:** [WenHao Wang](https://md.research.elamur.ai/free/en/authors/wenhao-wang/), Peizhi Niu, [Zhao Xu](https://md.research.elamur.ai/free/en/authors/zhao-xu/), Zhaoyu Chen, [Jian Du](https://md.research.elamur.ai/free/en/authors/jian-du/), Yaxin Du, [Xianghe Pang](https://md.research.elamur.ai/free/en/authors/xianghe-pang/), Keduan Huang, [Yanfeng Wang](https://md.research.elamur.ai/free/en/authors/yanfeng-wang/), Qiang Yan and [Siheng Chen](https://md.research.elamur.ai/free/en/authors/siheng-chen/) · **Year:** 2026 · **Venue:** [Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)](https://md.research.elamur.ai/free/en/venues/acl/) ([ACL 2026](https://md.research.elamur.ai/free/en/venues/acl/2026/)) · **Publisher:** [Association for Computational Linguistics](https://md.research.elamur.ai/free/en/publishers/association-for-computational-linguistics/) · **Licence:** [CC BY 4.0 (ACL Anthology)](https://creativecommons.org/licenses/by/4.0/)

**Links:** [Publisher's page](https://aclanthology.org/2026.acl-long.231/) · [PDF](https://aclanthology.org/2026.acl-long.231.pdf) · [DOI 10.18653/v1/2026.acl-long.231](https://doi.org/10.18653/v1/2026.acl-long.231) · [OpenAlex](https://openalex.org/W7166798430)

**Citations:** 0 citations (OpenAlex, 2026-10-14) · [7](https://md.research.elamur.ai/free/en/papers/wang-2026-mcp-flow-facilitating-llm-agents/cited-by/) in our library, of the 149,439 papers whose bibliographies we read

## Summary
LLM agents increasingly need to work with tools exposed through the Model Contextual Protocol (MCP), but even strong models handle real MCP servers poorly. Earlier MCP work is mostly evaluation-only, covers twenty servers or fewer, and depends on manual curation. MCP-Flow addresses these gaps with an automated pipeline. Web agents crawl six MCP marketplaces, including Smithery and Glama, to find and deploy servers. An LLM then synthesizes training data from the tool descriptions using few-shot generation, slot-fill revision, WizardLM-style evolution and multi-criteria filtering.

The resulting resource covers 1,166 servers and 11,536 tools, more than all previous MCP collections put together. Compact models fine-tuned on it select tools and format function calls better than much larger SOTA models. Retrieving MCP-Flow examples also helps closed models such as GPT-4o. On GAIA, using MCP-Flow for the initial tool call improves agent results while lowering inference cost. Data, code and checkpoints are public, which gives the community a scalable way to keep up with new MCP servers and to compare their quality.

## Key points
- Final dataset: 68,733 instruction–function call pairs and 6,439 trajectories. Of the collected servers, 356 returned valid responses usable for trajectories.
- Evaluation uses three test splits: seen, unseen tool and unseen server. It compares against 10+ strong LLMs and includes the GAIA agentic benchmark.
- Accuracy falls as the number of candidate tools grows. Models trained with larger candidate sets hold up better under this condition.
- Performance improves as training data grows. Tool accuracy nears 100%, while the AST metric still has room to improve.
- Two annotators reviewed 300 sampled items each, finding about 96% or higher label correctness and at most 2.5% unnecessary-tool noise.
- Resources are released at github.com/wwh0411/MCP-Flow.

*Our summary of the paper, in our own words — not its text. The work belongs to its authors; read it at the links above.*

## Institutions

- [University of Illinois Urbana-Champaign](https://md.research.elamur.ai/free/en/universities/university-of-illinois-urbana-champaign/) — University, Urbana, United States · 209 works · 71,394 citations
- [Shanghai Jiao Tong University](https://md.research.elamur.ai/free/en/universities/shanghai-jiao-tong-university/) — University, Shanghai, China · 212 works · 19,544 citations
- [Zhejiang University](https://md.research.elamur.ai/free/en/universities/zhejiang-university/) — University, Hangzhou, China · 224 works · 13,587 citations

📚 Shelves (4): [🖥️ Computer Science](https://md.research.elamur.ai/free/en/shelves/computer-science/) · 18,614 works · [🤖 Artificial Intelligence](https://md.research.elamur.ai/free/en/shelves/computer-science/artificial-intelligence/) · 17,965 works · [🎭 Arts and Humanities](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/) · 17,450 works · [🗣️ Language and Linguistics](https://md.research.elamur.ai/free/en/shelves/arts-and-humanities/language-and-linguistics/) · 17,296 works

## Cite

Cite as: WenHao Wang, Peizhi Niu, Zhao Xu, Zhaoyu Chen, Jian Du, Yaxin Du, Xianghe Pang, Keduan Huang, Yanfeng Wang, Qiang Yan and Siheng Chen. 2026. MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools. Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers).

The paper itself, not this page. BibTeX from the library's record of the work.

```bibtex
@inproceedings{wang2026mcp,
  title = {{MCP-Flow: Facilitating LLM Agents to Master Real-World, Diverse and Scaling MCP Tools}},
  author = {WenHao Wang, Peizhi Niu, Zhao Xu, Zhaoyu Chen, Jian Du, Yaxin Du, Xianghe Pang, Keduan Huang, Yanfeng Wang, Qiang Yan and Siheng Chen},
  booktitle = {Proceedings of the 64th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)},
  year = {2026},
  doi = {10.18653/v1/2026.acl-long.231},
  url = {https://doi.org/10.18653/v1/2026.acl-long.231}
}
```

- [← previous MASPO: Unifying Gradient Utilization, Probability Mass, and Signal Reliability for Robust and Sample-Efficient LLM Reasoning](https://md.research.elamur.ai/free/en/papers/fu-2026-maspo-unifying-gradient-utilization-probability/)
- [next → MetaScale: Test-Time Scaling with Evolving Meta-Thoughts](https://md.research.elamur.ai/free/en/papers/liu-2026-metascale-test-time-scaling-evolving/)
- [↑ back to papers of 2026](https://md.research.elamur.ai/free/en/papers/2026/page/2/)

## References

46 references, 15 of them with a card of ours. ↗ leads to the work, «find» searches for one we have no id for yet.

1. Anthropic. 2024a. Introducing claude 4. [https://www.anthropic.com/news/claude-4](https://www.anthropic.com/news/claude-4). Accessed: July 2025. [↗](https://www.anthropic.com/news/claude-4)
2. Anthropic. 2024b. Introducing the model context protocol. Online. Accessed: 2025-09-19. [find](https://scholar.google.com/scholar?q=Anthropic%2E+2024b%2E+Introducing+the+model+context+protocol%2E+Online%2E+Accessed%3A+2025%2D09%2D19%2E)
3. DeepSeek-AI. 2024. Deepseek-v3 technical report. Preprint, arXiv:2412.19437. [find](https://scholar.google.com/scholar?q=DeepSeek%2DAI%2E+2024%2E+Deepseek%2Dv3+technical+report%2E+Preprint%2C+arXiv%3A2412%2E19437%2E)
4. Yaxin Du, Yuanshuo Zhang, Xiyuan Yang, Yifan Zhou, Cheng Wang, Gongyi Zou, Xianghe Pang, Wenhao Wang, Menglan Chen, Shuo Tang, Zhiyu Li, Feiyu Xiong, and Siheng Chen. 2025. Infomosaic-bench: Evaluating multi-source information seeking in tool-augmented agents. Preprint, arXiv:2510.02271. — [arXiv:2510.02271](https://arxiv.org/abs/2510.02271) [find](https://scholar.google.com/scholar?q=Yaxin+Du%2C+Yuanshuo+Zhang%2C+Xiyuan+Yang%2C+Yifan+Zhou%2C+Cheng+Wang%2C+Gongyi+Zou%2C+Xianghe+Pang%2C+Wenhao+Wang%2C+Menglan+Chen%2C+Shuo+Tang%2C+Zhiyu+Li%2C+Feiyu+Xiong%2C+and+Siheng+Chen%2E+2025%2E+Infomosaic%2Dbench%3A+Evaluatin)
5. Shiqing Fan, Xichen Ding, Liang Zhang, and Linjian Mo. 2025. MCPToolBench++: A Large Scale AI Agent Model Context Protocol MCP Tool Use Benchmark. Preprint, arXiv:2508.07575. — [arXiv:2508.07575](https://arxiv.org/abs/2508.07575) [find](https://scholar.google.com/scholar?q=Shiqing+Fan%2C+Xichen+Ding%2C+Liang+Zhang%2C+and+Linjian+Mo%2E+2025%2E+MCPToolBench%2B%2B%3A+A+Large+Scale+AI+Agent+Model+Context+Protocol+MCP+Tool+Use+Benchmark%2E+Preprint%2C+arXiv%3A2508%2E07575%2E+%E2%80%94+%5BarXiv%3A2508%2E07575%5D%28http)
6. Xiang Fei, Xiawu Zheng, and Hao Feng. 2025. MCP-Zero: Proactive Toolchain Construction for LLM Agents from Scratch. Preprint, arXiv:2506.01056. — [arXiv:2506.01056](https://arxiv.org/abs/2506.01056) [find](https://scholar.google.com/scholar?q=Xiang+Fei%2C+Xiawu+Zheng%2C+and+Hao+Feng%2E+2025%2E+MCP%2DZero%3A+Proactive+Toolchain+Construction+for+LLM+Agents+from+Scratch%2E+Preprint%2C+arXiv%3A2506%2E01056%2E+%E2%80%94+%5BarXiv%3A2506%2E01056%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2506%2E01056%29)
7. Xuanqi Gao, Siyi Xie, Juan Zhai, Shqing Ma, and Chao Shen. 2025. MCP-RADAR: A Multi-Dimensional Benchmark for Evaluating Tool Use Capabilities in Large Language Models. Preprint, arXiv:2505.16700. — [arXiv:2505.16700](https://arxiv.org/abs/2505.16700) [find](https://scholar.google.com/scholar?q=Xuanqi+Gao%2C+Siyi+Xie%2C+Juan+Zhai%2C+Shqing+Ma%2C+and+Chao+Shen%2E+2025%2E+MCP%2DRADAR%3A+A+Multi%2DDimensional+Benchmark+for+Evaluating+Tool+Use+Capabilities+in+Large+Language+Models%2E+Preprint%2C+arXiv%3A2505%2E16700%2E+%E2%80%94+%5B)
8. Han Han, Tong Zhu, Xiang Zhang, Mengsong Wu, Hao Xiong, and Wenliang Chen. 2025. [NesTools: A Dataset for Evaluating Nested Tool Learning Abilities of Large Language Models](https://md.research.elamur.ai/free/en/papers/han-2025-nestools-dataset-evaluating-nested-tool/). Preprint, arXiv:2410.11805.
9. Mohammed Mehedi Hasan, Hao Li, Emad Fallahzadeh, Gopi Krishnan Rajbahadur, Bram Adams, and Ahmed E. Hassan. 2025. Model context protocol (mcp) at first glance: Studying the security and maintainability of mcp servers. Preprint, arXiv:2506.13538. — [arXiv:2506.13538](https://arxiv.org/abs/2506.13538) [find](https://scholar.google.com/scholar?q=Mohammed+Mehedi+Hasan%2C+Hao+Li%2C+Emad+Fallahzadeh%2C+Gopi+Krishnan+Rajbahadur%2C+Bram+Adams%2C+and+Ahmed+E%2E+Hassan%2E+2025%2E+Model+context+protocol+%28mcp%29+at+first+glance%3A+Studying+the+security+and+maintainabilit)
10. Edward J Hu, Yelong Shen, Phillip Wallis, Zeyuan Allen-Zhu, Yuanzhi Li, Shean Wang, Lu Wang, and Weizhu Chen. 2022. [LoRA: Low-rank adaptation of large language models](https://md.research.elamur.ai/free/en/papers/hu-2021-lora-low-rank-adaptation-large/). In International Conference on Learning Representations.
11. Woosuk Kwon, Zhuohan Li, Siyuan Zhuang, Ying Sheng, Lianmin Zheng, Cody Hao Yu, Joseph E. Gonzalez, Hao Zhang, and Ion Stoica. 2023. [Efficient memory management for large language model serving with pagedattention](https://md.research.elamur.ai/free/en/papers/kwon-2023-efficient-memory-management-large-language/). In Proceedings of the ACM SIGOPS 29th Symposium on Operating Systems Principles.
12. Xiaoxi Li, Jiajie Jin, Guanting Dong, Hongjin Qian, Yutao Zhu, Yongkang Wu, Ji-Rong Wen, and Zhicheng Dou. 2025. [Webthinker: Empowering large reasoning models with deep research capability](https://md.research.elamur.ai/free/en/papers/li-2025-webthinker-empowering-large-reasoning-models/). CoRR, abs/2504.21776.
13. Guozhao Mo, Wenliang Zhong, Jiawei Chen, Xuanang Chen, Yaojie Lu, Hongyu Lin, Ben He, Xianpei Han, and Le Sun. 2025. LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools? Preprint, arXiv:2508.01780. — [arXiv:2508.01780](https://arxiv.org/abs/2508.01780) [find](https://scholar.google.com/scholar?q=Guozhao+Mo%2C+Wenliang+Zhong%2C+Jiawei+Chen%2C+Xuanang+Chen%2C+Yaojie+Lu%2C+Hongyu+Lin%2C+Ben+He%2C+Xianpei+Han%2C+and+Le+Sun%2E+2025%2E+LiveMCPBench%3A+Can+Agents+Navigate+an+Ocean+of+MCP+Tools%3F+Preprint%2C+arXiv%3A2508%2E01780)
14. Shuquan Lian, Juncheng Liu, Yazhe Chen, Yuhong Chen, and Hui Li. 2026. Swe-agile: A software agent framework for efficiently managing dynamic reasoning context. Preprint, arXiv:2604.11716. [find](https://scholar.google.com/scholar?q=Shuquan+Lian%2C+Juncheng+Liu%2C+Yazhe+Chen%2C+Yuhong+Chen%2C+and+Hui+Li%2E+2026%2E+Swe%2Dagile%3A+A+software+agent+framework+for+efficiently+managing+dynamic+reasoning+context%2E+Preprint%2C+arXiv%3A2604%2E11716%2E)
15. OpenAI. 2024. [Gpt-4o system card](https://md.research.elamur.ai/free/en/papers/openai-2024-gpt-4o-system-card/). arXiv:2410.21276.
16. Zhiwei Lin, Bonan Ruan, Jiahao Liu, and Weibo Zhao. 2025. A large-scale evolvable dataset for model context protocol ecosystem and security analysis. arXiv preprint arXiv:2506.23474. — [arXiv:2506.23474](https://arxiv.org/abs/2506.23474) [find](https://scholar.google.com/scholar?q=Zhiwei+Lin%2C+Bonan+Ruan%2C+Jiahao+Liu%2C+and+Weibo+Zhao%2E+2025%2E+A+large%2Dscale+evolvable+dataset+for+model+context+protocol+ecosystem+and+security+analysis%2E+arXiv+preprint+arXiv%3A2506%2E23474%2E+%E2%80%94+%5BarXiv%3A2506%2E234)
17. Weiwen Liu, Xu Huang, Xingshan Zeng, Xinlong Hao, Shuai Yu, Dexun Li, Shuai Wang, Weinan Gan, Zhengying Liu, Yuanqing Yu, Zezhong Wang, Yuxian Wang, Wu Ning, Yutai Hou, Bin Wang, Chuhan Wu, Xinzhi Wang, Yong Liu, Yasheng Wang, and 8 others. 2024a. [ToolACE: Winning the Points of LLM Function Calling](https://md.research.elamur.ai/free/en/papers/liu-2024-toolace-winning-points-llm-function/).…
18. Zhiwei Liu, Jielin Qiu, Shiyu Wang, Jianguo Zhang, Zuxin Liu, Roshan Ram, Haolin Chen, Weiran Yao, Huan Wang, Shelby Heinecke, Silvio Savarese, and Caiming Xiong. 2025. MCPEval: Automatic MCP-based Deep Evaluation for AI Agent Models. Preprint, arXiv:2507.12806. [find](https://scholar.google.com/scholar?q=Zhiwei+Liu%2C+Jielin+Qiu%2C+Shiyu+Wang%2C+Jianguo+Zhang%2C+Zuxin+Liu%2C+Roshan+Ram%2C+Haolin+Chen%2C+Weiran+Yao%2C+Huan+Wang%2C+Shelby+Heinecke%2C+Silvio+Savarese%2C+and+Caiming+Xiong%2E+2025%2E+MCPEval%3A+Automatic+MCP%2Dbased+De)
19. Zuxin Liu, Thai Hoang, Jianguo Zhang, Ming Zhu, Tian Lan, Shirley Kokane, Juntao Tan, Weiran Yao, Zhiwei Liu, Yihao Feng, Rithesh Murthy, Liangwei Yang, Silvio Savarese, Juan Carlos Niebles, Huan Wang, Shelby Heinecke, and Caiming Xiong. 2024b. APIGen: Automated Pipeline for Generating Verifiable an… — [arXiv:2406.18518](https://arxiv.org/abs/2406.18518) [find](https://scholar.google.com/scholar?q=Zuxin+Liu%2C+Thai+Hoang%2C+Jianguo+Zhang%2C+Ming+Zhu%2C+Tian+Lan%2C+Shirley+Kokane%2C+Juntao+Tan%2C+Weiran+Yao%2C+Zhiwei+Liu%2C+Yihao+Feng%2C+Rithesh+Murthy%2C+Liangwei+Yang%2C+Silvio+Savarese%2C+Juan+Carlos+Niebles%2C+Huan+Wang)
20. Zhiling Luo, Xiaorong Shi, Xuanrui Lin, and Jinyang Gao. 2025a. Evaluation report on mcp servers. arXiv preprint arXiv:2504.11094. — [arXiv:2504.11094](https://arxiv.org/abs/2504.11094) [find](https://scholar.google.com/scholar?q=Zhiling+Luo%2C+Xiaorong+Shi%2C+Xuanrui+Lin%2C+and+Jinyang+Gao%2E+2025a%2E+Evaluation+report+on+mcp+servers%2E+arXiv+preprint+arXiv%3A2504%2E11094%2E+%E2%80%94+%5BarXiv%3A2504%2E11094%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2504%2E11094%29)
21. Ziyang Luo, Zhiqi Shen, Wenzhuo Yang, Zirui Zhao, Prathyusha Jwalapuram, Amrita Saha, Doyen Sahoo, Silvio Savarese, Caiming Xiong, and Junnan Li. 2025b. MCP-Universe: Benchmarking Large Language Models with Real-World Model Context Protocol Servers. Preprint, arXiv:2508.14704. — [arXiv:2508.14704](https://arxiv.org/abs/2508.14704) [find](https://scholar.google.com/scholar?q=Ziyang+Luo%2C+Zhiqi+Shen%2C+Wenzhuo+Yang%2C+Zirui+Zhao%2C+Prathyusha+Jwalapuram%2C+Amrita+Saha%2C+Doyen+Sahoo%2C+Silvio+Savarese%2C+Caiming+Xiong%2C+and+Junnan+Li%2E+2025b%2E+MCP%2DUniverse%3A+Benchmarking+Large+Language+Model)
22. Leland McInnes, John Healy, and James Melville. 2018. [Umap: Uniform manifold approximation and projection for dimension reduction](https://md.research.elamur.ai/free/en/papers/mcinnes-2018-umap-uniform-manifold-approximation-projection/). arXiv preprint arXiv:1802.03426.
23. AI Meta. 2024. Introducing meta llama 3: The most capable openly available llm to date. Meta AI, 2(5):6. [find](https://scholar.google.com/scholar?q=AI+Meta%2E+2024%2E+Introducing+meta+llama+3%3A+The+most+capable+openly+available+llm+to+date%2E+Meta+AI%2C+2%285%29%3A6%2E)
24. Grégoire Mialon, Clémentine Fourrier, Craig Swift, Thomas Wolf, Yann LeCun, and Thomas Scialom. 2023. [Gaia: a benchmark for general ai assistants](https://md.research.elamur.ai/free/en/papers/mialon-2023-gaia-benchmark-general-ai-assistants/). Preprint, arXiv:2311.12983.
25. Preprint, Shishir G. Patil, Huanzhi Mao, Fanjia Yan, Charlie Cheng-Jie Ji, Vishnu Suresh, Ion Stoica, and Joseph E. Gonzalez. 2025. The Berkeley Function Calling Leaderboard (BFCL): From Tool Use to Agentic Evaluation of Large Language Models. In Forty-Second International Conference on Machine Lear… [find](https://scholar.google.com/scholar?q=Preprint%2C+Shishir+G%2E+Patil%2C+Huanzhi+Mao%2C+Fanjia+Yan%2C+Charlie+Cheng%2DJie+Ji%2C+Vishnu+Suresh%2C+Ion+Stoica%2C+and+Joseph+E%2E+Gonzalez%2E+2025%2E+The+Berkeley+Function+Calling+Leaderboard+%28BFCL%29%3A+From+Tool+Use+to+A)
26. Karl Pearson. 1901. On lines and planes of closest fit to systems of points in space. Philosophical Magazine, 2(11):559–572. [find](https://scholar.google.com/scholar?q=Karl+Pearson%2E+1901%2E+On+lines+and+planes+of+closest+fit+to+systems+of+points+in+space%2E+Philosophical+Magazine%2C+2%2811%29%3A559%E2%80%93572%2E)
27. Yujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu, Lan Yan, Yaxi Lu, Yankai Lin, Xin Cong, Xiangru Tang, Bill Qian, Sihan Zhao, Lauren Hong, Runchu Tian, Ruobing Xie, Jie Zhou, Mark Gerstein, Dahai Li, Zhiyuan Liu, and Maosong Sun. 2023. [ToolLLM: Facilitating Large Language Models to Master 16000+ Real…](https://md.research.elamur.ai/free/en/papers/qin-2023-toolllm-facilitating-large-language-models/)
28. Jie Ren, Samyam Rajbhandari, Reza Yazdani Aminabadi, Olatunji Ruwase, Shuangyan Yang, Minjia Zhang, Dong Li, and Yuxiong He. 2021. [{Zero-offload}: Democratizing {billion-scale} model training](https://md.research.elamur.ai/free/en/papers/ren-2021-zero-offload-democratizing-billion-scale/). In 2021 USENIX Annual Technical Conference (USENIX ATC 21), pages 551–564.
29. Yongliang Shen, Kaitao Song, Xu Tan, Wenqi Zhang, Kan Ren, Siyu Yuan, Weiming Lu, Dongsheng Li, and Yueting Zhuang. 2024. TaskBench: Benchmarking Large Language Models for Task Automation. Advances in Neural Information Processing Systems, 37:4540–4574. [find](https://scholar.google.com/scholar?q=Yongliang+Shen%2C+Kaitao+Song%2C+Xu+Tan%2C+Wenqi+Zhang%2C+Kan+Ren%2C+Siyu+Yuan%2C+Weiming+Lu%2C+Dongsheng+Li%2C+and+Yueting+Zhuang%2E+2024%2E+TaskBench%3A+Benchmarking+Large+Language+Models+for+Task+Automation%2E+Advances+in)
30. Zhuocheng Shen. 2024. LLM With Tools: A Survey. Preprint, arXiv:2409.18807. — [arXiv:2409.18807](https://arxiv.org/abs/2409.18807) [find](https://scholar.google.com/scholar?q=Zhuocheng+Shen%2E+2024%2E+LLM+With+Tools%3A+A+Survey%2E+Preprint%2C+arXiv%3A2409%2E18807%2E+%E2%80%94+%5BarXiv%3A2409%2E18807%5D%28https%3A%2F%2Farxiv%2Eorg%2Fabs%2F2409%2E18807%29)
31. Hao Song, Yiming Shen, Wenxuan Luo, Leixin Guo, Ting Chen, Jiashui Wang, Beibei Li, Xiaosong Zhang, and Jiachi Chen. 2025. Beyond the Protocol: Unveiling Attack Vectors in the Model Context Protocol Ecosystem. Preprint, arXiv:2506.02040. — [arXiv:2506.02040](https://arxiv.org/abs/2506.02040) [find](https://scholar.google.com/scholar?q=Hao+Song%2C+Yiming+Shen%2C+Wenxuan+Luo%2C+Leixin+Guo%2C+Ting+Chen%2C+Jiashui+Wang%2C+Beibei+Li%2C+Xiaosong+Zhang%2C+and+Jiachi+Chen%2E+2025%2E+Beyond+the+Protocol%3A+Unveiling+Attack+Vectors+in+the+Model+Context+Protocol+E)
32. Qwen Team. 2025. [Qwen3 technical report](https://md.research.elamur.ai/free/en/papers/yang-2025-qwen3-technical-report/). Preprint, arXiv:2505.09388.
33. Laurens van der Maaten and Geoffrey Hinton. 2008. Visualizing data using t-sne. Journal of Machine Learning Research, 9:2579–2605. [find](https://scholar.google.com/scholar?q=Laurens+van+der+Maaten+and+Geoffrey+Hinton%2E+2008%2E+Visualizing+data+using+t%2Dsne%2E+Journal+of+Machine+Learning+Research%2C+9%3A2579%E2%80%932605%2E)
34. WenHao Wang, Xiaoyu Liang, Rui Ye, Jingyi Chai, Siheng Chen, and Yanfeng Wang. 2024. Knowl-edgeSG: Privacy-preserving synthetic text generation with knowledge distillation from server. In Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing, pages 7677–7695, Miami,… [find](https://scholar.google.com/scholar?q=WenHao+Wang%2C+Xiaoyu+Liang%2C+Rui+Ye%2C+Jingyi+Chai%2C+Siheng+Chen%2C+and+Yanfeng+Wang%2E+2024%2E+Knowl%2DedgeSG%3A+Privacy%2Dpreserving+synthetic+text+generation+with+knowledge+distillation+from+server%2E+In+Proceedings+)
35. WenHao Wang, Zijie Yu, Rui Ye, Jianqing Zhang, Guangyi Liu, Liang Liu, Siheng Chen, and Yanfeng Wang. 2025a. FedMABench: Benchmarking mobile GUI agents on decentralized heterogeneous user data. In Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing, pages 26387–264… [find](https://scholar.google.com/scholar?q=WenHao+Wang%2C+Zijie+Yu%2C+Rui+Ye%2C+Jianqing+Zhang%2C+Guangyi+Liu%2C+Liang+Liu%2C+Siheng+Chen%2C+and+Yanfeng+Wang%2E+2025a%2E+FedMABench%3A+Benchmarking+mobile+GUI+agents+on+decentralized+heterogeneous+user+data%2E+In+Pro)
36. Wenhao Wang, Mengying Yuan, Zijie Yu, Guangyi Liu, Rui Ye, Tian Jin, Siheng Chen, and Yanfeng Wang. 2025b. Mobilea3gent: Training mobile gui agents using decentralized self-sourced data from diverse users. Preprint, arXiv:2502.02982. [find](https://scholar.google.com/scholar?q=Wenhao+Wang%2C+Mengying+Yuan%2C+Zijie+Yu%2C+Guangyi+Liu%2C+Rui+Ye%2C+Tian+Jin%2C+Siheng+Chen%2C+and+Yanfeng+Wang%2E+2025b%2E+Mobilea3gent%3A+Training+mobile+gui+agents+using+decentralized+self%2Dsourced+data+from+diverse+u)
37. Jialong Wu, Baixuan Li, Runnan Fang, Wenbiao Yin, Liwen Zhang, Zhengwei Tao, Dingchu Zhang, Zekun Xi, Gang Fu, Yong Jiang, Pengjun Xie, Fei Huang, and Jingren Zhou. 2025. [Webdancer: Towards autonomous information seeking agency](https://md.research.elamur.ai/free/en/papers/wu-2025-webdancer-towards-autonomous-information-seeking/). Preprint, arXiv:2505.22648.
38. Mengsong Wu, Tong Zhu, Han Han, Chuanyuan Tan, Xiang Zhang, and Wenliang Chen. 2024. Seal-Tools: Self-Instruct Tool Learning Dataset for Agent Tuning and Detailed Benchmark. Preprint, arXiv:2405.08355. — [arXiv:2405.08355](https://arxiv.org/abs/2405.08355) [find](https://scholar.google.com/scholar?q=Mengsong+Wu%2C+Tong+Zhu%2C+Han+Han%2C+Chuanyuan+Tan%2C+Xiang+Zhang%2C+and+Wenliang+Chen%2E+2024%2E+Seal%2DTools%3A+Self%2DInstruct+Tool+Learning+Dataset+for+Agent+Tuning+and+Detailed+Benchmark%2E+Preprint%2C+arXiv%3A2405%2E08355)
39. Can Xu, Qingfeng Sun, Kai Zheng, Xiubo Geng, Pu Zhao, Jiazhan Feng, Chongyang Tao, Qingwei Lin, and Daxin Jiang. 2023. [WizardLM: Empowering Large Pre-Trained Language Models to Follow Complex Instructions](https://md.research.elamur.ai/free/en/papers/xu-2023-wizardlm-empowering-large-pre-trained/). In The Twelfth International Conference on Learning Representations.
40. Yunhe Yan, Shihe Wang, Jiajun Du, Yexuan Yang, Yuxuan Shan, Qichen Qiu, Xianqing Jia, Xinge Wang, Xin Yuan, Xu Han, Mao Qin, Yinxiao Chen, Chen Peng, Shangguang Wang, and Mengwei Xu. 2025. MCPWorld: A Unified Benchmarking Testbed for API, GUI, and Hybrid Computer Use Agents. Preprint, arXiv:2506.076… [find](https://scholar.google.com/scholar?q=Yunhe+Yan%2C+Shihe+Wang%2C+Jiajun+Du%2C+Yexuan+Yang%2C+Yuxuan+Shan%2C+Qichen+Qiu%2C+Xianqing+Jia%2C+Xinge+Wang%2C+Xin+Yuan%2C+Xu+Han%2C+Mao+Qin%2C+Yinxiao+Chen%2C+Chen+Peng%2C+Shangguang+Wang%2C+and+Mengwei+Xu%2E+2025%2E+MCPWorld%3A+A)
41. Shunyu Yao, Noah Shinn, Pedram Razavi, and Karthik Narasimhan. 2024. [$τ $-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://md.research.elamur.ai/free/en/papers/yao-2024-tau-bench-benchmark-tool/). Preprint, arXiv:2406.12045.
42. Ming Yin, Dinghan Shen, Silei Xu, Jianbing Han, Sixun Dong, Mian Zhang, Yebowen Hu, Shujian Liu, Simin Ma, Song Wang, Sathish Reddy Indurthi, Xun Wang, Yiran Chen, and Kaiqiang Song. 2025. LiveMCP-101: Stress Testing and Diagnosing MCP-enabled Agents on Challenging Queries. Preprint, arXiv:2508.1576… — [arXiv:2508.15760](https://arxiv.org/abs/2508.15760) [find](https://scholar.google.com/scholar?q=Ming+Yin%2C+Dinghan+Shen%2C+Silei+Xu%2C+Jianbing+Han%2C+Sixun+Dong%2C+Mian+Zhang%2C+Yebowen+Hu%2C+Shujian+Liu%2C+Simin+Ma%2C+Song+Wang%2C+Sathish+Reddy+Indurthi%2C+Xun+Wang%2C+Yiran+Chen%2C+and+Kaiqiang+Song%2E+2025%2E+LiveMCP%2D101)
43. Siyu Yuan, Kaitao Song, Jiangjie Chen, Xu Tan, Yongliang Shen, Ren Kan, Dongsheng Li, and Deqing Yang. 2024. EASYTOOL: Enhancing LLM-based Agents with Concise Tool Instruction. Preprint, arXiv:2401.06201. [find](https://scholar.google.com/scholar?q=Siyu+Yuan%2C+Kaitao+Song%2C+Jiangjie+Chen%2C+Xu+Tan%2C+Yongliang+Shen%2C+Ren+Kan%2C+Dongsheng+Li%2C+and+Deqing+Yang%2E+2024%2E+EASYTOOL%3A+Enhancing+LLM%2Dbased+Agents+with+Concise+Tool+Instruction%2E+Preprint%2C+arXiv%3A2401%2E06)
44. Xinyu Zhang, Huiyu Xu, Zhongjie Ba, Zhibo Wang, Yuan Hong, Jian Liu, Zhan Qin, and Kui Ren. 2024. [find](https://scholar.google.com/scholar?q=Xinyu+Zhang%2C+Huiyu+Xu%2C+Zhongjie+Ba%2C+Zhibo+Wang%2C+Yuan+Hong%2C+Jian+Liu%2C+Zhan+Qin%2C+and+Kui+Ren%2E+2024%2E)
45. PrivacyAsst: Safeguarding User Privacy in Tool-Using Large Language Model Agents. IEEE Transactions on Dependable and Secure Computing, pages 1–16. [find](https://scholar.google.com/scholar?q=PrivacyAsst%3A+Safeguarding+User+Privacy+in+Tool%2DUsing+Large+Language+Model+Agents%2E+IEEE+Transactions+on+Dependable+and+Secure+Computing%2C+pages+1%E2%80%9316%2E)
46. Yaowei Zheng, Richong Zhang, Junhao Zhang, Yanhan Ye, Zheyan Luo, Zhangchi Feng, and Yongqiang Ma. 2024. [Llamafactory: Unified efficient fine-tuning of 100+ language models](https://md.research.elamur.ai/free/en/papers/zheng-2024-llamafactory-unified-efficient-fine-tuning/). In Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 3: System Demonstrations),…

*Updated 2 November 2026*