Lune

ACL Findings2026

ToolGrad: Efficient Tool-use Dataset Generation with Textual "Gradients"

Zhongyi Zhou, Kohei Uehara, Haoyu Zhang, Jingtao Zhou, Lin Gu, Ruofei Du, Zheng Xu, Tatsuya Harada

Abstract

Prior work synthesizes tool-use LLM datasets by first generating a user query, followed by complex tool-use annotations like depth-first search (DFS). This leads to inevitable annotation failures and low efficiency in data generation. We introduce ToolGrad, an agentic framework that inverts this paradigm. ToolGrad first constructs valid tool-use chains through an iterative process guided by textual "gradients", and then synthesizes corresponding user queries. This "answer-first" approach led to ToolGrad-500, a dataset generated with more complex tool use, lower cost, and almost 100% pass rate. Experiments show that ToolGrad models outperform those trained on expensive baseline datasets and proprietary LLMs. The ToolGrad source code, dataset, and models are available at https://github.com/ zhongyi-zhou/toolgrad.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

Questions to start from

Lune can draw on

the full paper · related work

Get the answer

Free to start. No credit card required.

Lineage

  • Gorilla: Large Language Model Connected with Massive APIs cites Toolformer: Language Models Can Teach Themselves to Use Tools
  • Gorilla: Large Language Model Connected with Massive APIs cites HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
  • ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs cites Gorilla: Large Language Model Connected with Massive APIs
  • ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs cites Toolformer: Language Models Can Teach Themselves to Use Tools
  • ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs cites HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face
  • HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging Face cites Toolformer: Language Models Can Teach Themselves to Use Tools
Builds onCited byLeft to right by year; the more cited, the higher.

Builds on23

  1. Toolformer: Language Models Can Teach Themselves to Use ToolsTimo Schick, Jane Dwivedi-Yu, Roberto Dessì, Roberta Raileanu et al.NeurIPS 2023 · 5,989 citations
  2. Generative Agents: Interactive Simulacra of Human BehaviorJoon Sung Park, Joseph C. O'Brien, Carrie Jun Cai, Meredith Ringel Morris et al.UIST 2023 · 1,882 citations
  3. HuggingGPT: Solving AI Tasks with ChatGPT and its Friends in Hugging FaceYongliang Shen, Kaitao Song, Xu Tan, Dongsheng Li et al.NeurIPS 2023 · 1,778 citations
  4. Gorilla: Large Language Model Connected with Massive APIsShishir G. Patil, Tianjun Zhang, Xin Wang, Joseph E. GonzalezNeurIPS 2024 · 1,715 citations
  5. ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIsYujia Qin, Shihao Liang, Yining Ye, Kunlun Zhu et al.ICLR 2024 · 1,469 citations

Related papers

  1. ToolACE-MT: Non-Autoregressive Generation for Agentic Multi-Turn InteractionXingshan Zeng, Weiwen Liu, Lingzhi Wang, Liangyou Li et al.ICLR 2026 · 15 citations
  2. TaskCraft: Automated Generation of Agentic TasksDingfeng Shi, Jingyi Cao, Qianben Chen, Weichen Sun et al.ICLR 2026 · 49 citations
  3. ToolOmni: Enabling Open-World Tool Use via Agentic learning with Proactive Retrieval and Grounded ExecutionShouzheng Huang, Meishan Zhang, Baotian Hu, Min ZhangACL 2026
  4. Mock Worlds, Real Skills: Building Small Agentic Language Models with Synthetic Tasks, Simulated Environments, and Rubric-Based RewardsYuanjie Lyu, Chengyu Wang, Lei Shen, Jun Huang et al.ACL 2026 · 3 citations
  5. Empowering LLM Tool Invocation with Tool-call Reward ModelDa Ma, Ziyue Yang, Hongshen Xu, Haotian Fang et al.ICLR 2026
Dusk over the sea between two cliffs drawn in fine vertical lines