TaskCraft: Automated Generation of Agentic Tasks

Dingfeng Shi, Jingyi Cao, Chen, Weichen Sun, Weizhen Li, Hongxuan Lu, Fangchen Dong, tianrui, King Zhu, Minghao Yang, Jian Yang, Ge Zhang, Jiaheng Liu, Changwang ZHANG, Jun Wang, Yuchen Eleanor Jiang, Zhou

TaskCraft: Automated Generation of Agentic Tasks: 23 upvotes on Hugging Face Daily Papers, #10 of 40 papers on 2025-06-17. Day-by-day upvote history. It lost 10 votes when the Hub removed votes in bulk.

Agentic tasks, which require multi-step problem solving with autonomy, tool use, and adaptive reasoning, are becoming increasingly central to the advancement of NLP and AI. However, existing instruction data lacks tool interaction, and current agentic benchmarks rely on costly human annotation, limiting their scalability. We introduce TaskCraft, an automated workflow for generating difficulty-scalable, multi-tool, and verifiable agentic tasks with execution trajectories. TaskCraft expands atomic tasks using depth-based and width-based extensions to create structurally and hierarchically complex challenges. Empirical results show that these tasks improve prompt optimization in the generation workflow and enhance supervised fine-tuning of agentic foundation models. We present a large-scale synthetic dataset of approximately 36,000 tasks with varying difficulty to support future research on agent tuning and evaluation.

Paper page on Hugging Face · arXiv

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.