Tool-Genesis: A Task-Driven Tool Creation Benchmark for Self-Evolving Language Agent

AI & ML interests

Tool creation benchmark; task-driven tool generation; self-evolving language agents; evaluation and meta-learning.

Recent Activity

subway-jack  authored a paper 2 days ago

ClawMark: A Living-World Benchmark for Multi-Turn, Multi-Day, Multimodal Coworker Agents

subway-jack  updated a model about 2 months ago

tool-genesis/Tool-Genesis-Qwen3-8B-SFT

subway-jack  published a model about 2 months ago

tool-genesis/Tool-Genesis-Qwen3-8B-SFT

View all activity

Team members 1