Skip to content
EventMonitoring

Renmin University of China, Fudan University and others propose the ToolSpace agent environment synthesis framework

1 reports1 reporting sourcesLatest report

Start here

AI overview

Teams from Renmin University of China, Fudan University, and Shanghai Jiao Tong University propose ToolSpace, a tool-centric environment synthesis framework that extracts tool dependencies from more than 200,000 interaction trajectories and builds a composition graph, synthesizing environment data on demand and generating replay-verifiable cross-environment tasks. ToolSpace-744B-A40B, based on this framework, undergoes only supervised fine-tuning and raises its average score on seven long-horizon tool benchmarks from 44.6 to 56.6, matching Claude Opus 5.

Generated by AI from reports · Updated 1 days ago

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 environments
  2. · 1 reports· Attention18

    Renmin University of China, Fudan University and others propose the ToolSpace agent environment synthesis frameworkThis event

Progress timeline

Nov 17
  1. WeChat · Synced (Jiqizhixin)
    Renmin University, Fudan and others propose ToolSpace: a 744B model with only supervised fine-tuning matches Claude Opus 5 on the average score across seven benchmarks

    Teams from Renmin University, Fudan University and Shanghai Jiao Tong University propose ToolSpace, a tool-centric environment synthesis framework; its 744B model matches Claude Opus 5 on the average score across seven long-horizon tool benchmarks. The framework extracts tool dependencies from more than 200,000 interaction trajectories and builds a composition graph, synthesizes environment data on demand, and generates cross-environment tasks that can be verified by replay; ToolSpace-744B-A40B uses only supervised fine-tuning, and its seven-benchmark average score rises from 44.6 to 56.6.

Related discussion

Total 1 items

Attention trend

New sources per day

1 in 4 days·most 1 (Nov 17)·today 0

  • Nov 17: 1 new sources (1 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

No comparable trend data