TAU-bench D
AI benchmark · Agentic
What is TAU-bench?
TAU-bench measures how reliably language agents use domain-specific API tools and follow policy guidelines in simulated conversations with users in retail and airline domains.
Enterprise work mostly
“a language agent provided with domain-specific API tools and policy guidelines”
arxiv.org/abs/2406.12045 ↗
Paper: arxiv.org/abs/2406.12045 ↗
Lineage
Benchmarks this one is built on and built from: versions, subsets, extensions and the indexes that combine them.
Derived benchmarks
TAU-bench Airline subset
Tier D
Long tail: little or no usage data yet.
How much stands behind a tier: usage, who backs it, a confirmed line from its own site or paper, and a clear read on X. High with three of the four, medium with two, low otherwise.
- no usage data
- in curated RL directories (1 pt)
On X · mixed, low buzz, from 4 posts about TAU-bench in the last month
Small discussion: one researcher reports widespread grading defects in the TAU-banking tasks, while others cite tau-bench's pass^k metric and scoring setup as useful references.
How we got to tier D
- Adoption: no usage data. Tier D.
- On X: mixed, low buzz. “Small discussion: one researcher reports widespread grading defects in the TAU-banking tasks, while others cite tau-bench's pass^k metric and scoring setup as useful references.” No move.
- In curated RL directories: 1 point, a floor of none.
- Confirmed: a line from its own site or paper places it.
A clear view on X moves a tier one step up or down; most entries don't move. How tiers work.
Where TAU-bench sits
Its domain on the map, live. Hover a logo for its name; click to open it. Open it on the full map
Next: browse all benchmarks. Entry from the RL Research daily scrape of public sources, 2026-11-05 snapshot.