cs.CLNov 3, 2026

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, 

Organizations: Renmin University of China · Fudan University · Shanghai Jiao Tong University

Abstract

Large language models are deployed as long-horizon agents that compose diverse tools across MCP services into executable workflows. Existing MCP environment-scaling methods are data-centric: they first synthesize a database and scenario, then derive tools and tasks from them. As a result, tool interfaces may not match real ones, tool compositions are not grounded in execution, and tasks rarely span more than one environment. We propose ToolSpace, a tool-centric framework that reverses this order. ToolSpace mines data, state, and retry dependencies from adjacent calls in execution traces of real MCP services and open agent corpora, using deterministic rules rather than LLM judgment, and clusters the resulting weighted tool-composition graph into environments. Databases are synthesized only for state-mutating environments, while query and stateless tools replay recorded returns. ToolSpace then performs state-aware random walks with rollback and decompiles each chain into a natural-language task with assertion-based checks, keeping only samples that replay successfully from the initial state. Applied to AutomationBench and tau3-Bench Banking, the pipeline produces harder Pro versions on which 7 frontier models drop by up to 38.2 points. Across seven long-horizon tool-use benchmarks, ToolSpace raises Qwen3.6-35B-A3B from 23.0 to 41.0 average score (43.2 with RL) and GLM-5.2 from 44.6 to 56.6, on par with Claude Opus 5. Ablations show that execution-witnessed edges clearly outperform LLM-judged ones, and performance keeps improving with data and environment scale.

Figures & tables

Explore similar work

CardsList
  1. HyperTool: Beyond Step-Wise Tool Calls for Tool-Augmented Agents

    Jun 11, 2026Yaxin Du, Yifan Zhou, Yujie Ge +7Tool-Augmented Language Model AgentsLLM Agent Workflow Optimization

  2. EnvFactory: Scaling Tool-Use Agents via Executable Environments Synthesis and Robust RL

    May 18, 2026Minrui Xu, Zilin Wang, Mengyi DENG +12Tool-Augmented Language Model AgentsAgentic RL