by sierra-research · LLM 插件 · ★ 1.3k
$\tau$-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains 🚀 τ³-bench is here! From text-only to multimodal, knowledge-aware agent evaluation. Voice full-duplex · Knowledge ret
| Stars | 1,333 |
| Forks | 343 |
| Language | Python |
| Category | LLM 插件 |
| License | MIT |
| Quality Score | 58.678/100 |
| Open Issues | 120 |
| Last Updated | 2026-06-10 |
| Created | 2025-06-09 |
| Platforms | python |
| Est. Tokens | ~22491k |
These tools work well together with tau2-bench for enhanced workflows:
Explore other popular llm 插件 tools:
tau2-bench is τ-Bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains. It is categorized as a LLM 插件 with 1.3k GitHub stars.
tau2-bench is primarily written in Python. It covers topics such as ai, benchmark, conversational-agents.
You can find installation instructions and usage details in the tau2-bench GitHub repository at github.com/sierra-research/tau2-bench. The project has 1.3k stars and 343 forks, indicating an active community.
tau2-bench is released under the MIT license, making it free to use and modify according to the license terms.