Skip to content
EventPast event

ToolSpace: Tool-centric synthesis of long-horizon Agent environments

1 reports1 reporting sourcesLatest report

Start here

AI overview

On November 3, 2026, Hugging Face Daily Papers included the paper ToolSpace, which proposes a tool-first framework: mine execution traces from real MCP services and open agent corpora, use deterministic rules to extract data, state and retry dependencies from adjacent calls, cluster a weighted tool-combination graph into environments, then generate tasks via state-aware random walks with rollback and decompile them into natural-language tasks with assertions, retaining only samples that can be successfully replayed from the initial state, for synthesizing a multi-environment tool-use benchmark and training data.

Generated by AI from reports · Updated 15 days ago

Attention and developments

Attention, hourly

Now 32, 0% in 24 hours·Peak 33 (Nov 15 08:00)

Nov 14Nov 15Nov 16Nov 17Nov 18Nov 19Nov 20Now 32

Storyline

Developments on the same subject and issue, from earliest to latest

2 events
  1. · 1 reports· Attention32

    ToolSpace: Tool-centric synthesis of long-horizon Agent environmentsThis event

  2. · 1 reports· Attention18
    Renmin University of China, Fudan University and others propose the ToolSpace agent environment synthesis framework

Progress timeline

Nov 15
Nov 3
  1. Hugging Face Daily Papers
    ToolSpace: Tool-Centric Environment Synthesis Scaling for Long-Horizon Agents

    The paper proposes ToolSpace, a tool-first framework that synthesizes multi-environment tool-use benchmarks and training data by mining execution traces from real MCP services and open agent corpora. In contrast to data-centric approaches that first synthesize databases and then derive tools, it mines data, state, and retry dependencies from adjacent calls using deterministic rules, clusters a weighted tool-combination graph into environments, and generates tasks via state-aware random walks with rollback, decompiling them into natural-language tasks with assertion checks and retaining only samples that can be successfully replayed from the initial state. On AutomationBench and tau3-Bench Banking, this pipeline generates harder Pro versions, with 7 frontier models dropping by up to 38.2 points. On seven long-horizon tool-use benchmarks, ToolSpace raises the average score of Qwen3.6-35B-A3B from 23.0 to 41.0 (43.2 after RL) and GLM-5.2 from 44.6 to 56.6, comparable to Claude Opus 5.

Related discussion

Total 1 items

Attention trend

New sources per day

1 in 6 days·most 1 (Nov 15)·today 0

  • Nov 15: 1 new sources (0 outlets, 1 accounts)
  • Nov 16: 0 new sources (0 outlets, 0 accounts)
  • Nov 17: 0 new sources (0 outlets, 0 accounts)
  • Nov 18: 0 new sources (0 outlets, 0 accounts)
  • Nov 19: 0 new sources (0 outlets, 0 accounts)
  • Nov 20: 0 new sources (0 outlets, 0 accounts)

Hourly attention

Current attention 32·Peak in the comparable period 33 (Nov 15 08:00)·Change over the comparable past 24 hours 0%

010203040Nov 1303:00Nov 1511:00Nov 1718:00Nov 2002:00