ToolSpace合成MCP智能体环境
Hugging Face · Papers报道，Guanting Dong等25位作者提出ToolSpace，利用真实MCP服务和开放智能体语料库的执行轨迹构建工具中心环境。该框架以确定性规则提取工具依赖，通过带回滚的状态感知随机游走和基于断言的检查，保留可成功重放的任务。论文称，7个前沿模型在更难的AutomationBench和tau3-Bench Banking Pro版本上最多下降38.2分，Qwen3.6-35B-A3B和GLM-5.2在7个长程工具使用基准上的成绩也得到提升。
ToolSpace提供了一种基于真实执行过程扩展多环境MCP任务的明确方法，其报告的基准成绩使它成为长程智能体环境构建与评测方向的重要研究进展。
Computer Science > Computation and Language
arXiv:2611.05036 (cs)
[Submitted on 3 Nov 2026]
Title:ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents
Authors:Guanting Dong, Zhichao Sun, Xinyu Yang, Rui Wang, Xin Deng, Jiajie Jin, Zhixiong Yang, Junhao Huang, Han Han, Mingyu Ma, Xiaotao Wang, Yuyang Hu, Xiaoshuai Song, Xiaoxi Li, Jiejun Tan, Zhecan Wang, Shihan Dou, Honglin Guo, Zhiheng Xi, Tao Gui, Tao Ji, Qi Zhang, Yutao Zhu, Ji-Rong Wen, Zhicheng Dou
View a PDF of the paper titled ToolSpace: Scaling Tool-Centric Environment Synthesis for Long-Horizon Agents, by Guanting Dong and 24 other authors
#ToolSpace#AutomationBench#tau3-Bench Banking#Qwen3.6-35B-A3B#GLM-5.2#Claude Opus 5