WildToolBench

by yupeijei1997 · Agent Tool · ★ 40

About WildToolBench

Benchmarking LLM Tool-Use in the Wild πŸ“– English β€’ δΈ­ζ–‡ β€’ πŸ“š ICLR 2026 Paper β€’ 🌐 Project Page πŸ“– Overview Fulfilling user needs through Large Language Model multi-turn, multi-step tool-use is rarely a straightforward process. Real user interactions are inherently wild, being unpredictable, messy, and flexible.

Quick Facts

Stars40
Forks4
LanguagePython
CategoryAgent Tool
Quality Score60.8970415430589/100
Open Issues1
Last Updated2026-09-01
Created2026-01-03
Platformspython
Est. Tokens~14k

Compatible Skills

These tools work well together with WildToolBench for enhanced workflows:

  • MCPToolBenchPP β€” semantic(0.30)+complementary+same_lang+similar_pop+shared_platform (55%)
  • AgentVista β€” semantic(0.28)+complementary+same_lang+similar_pop+shared_platform (55%)
  • toolbench β€” semantic(0.25)+complementary+same_lang+similar_pop+shared_platform (54%)

More Agent Tool Tools

Explore other popular agent tool tools:

View all Agent Tool tools β†’

Popular Python Agent Tools

Frequently Asked Questions

What is WildToolBench?

WildToolBench is (ICLR 2026)Benchmarking LLM Tool-Use in the Wild. It is categorized as a Agent Tool with 40 GitHub stars.

What programming language is WildToolBench written in?

WildToolBench is primarily written in Python.

How do I install or use WildToolBench?

You can find installation instructions and usage details in the WildToolBench GitHub repository at github.com/yupeijei1997/WildToolBench. The project has 40 stars and 4 forks, indicating an active community.

View on GitHub → Browse Agent Tool tools