TAU 2 Bench RL Env (Prime Intellect)

Fresh

τ²-bench evaluation environment

Type: RL Env
Publisher: Prime Intellect
Tags: Tool Use Tool Agent User User Sim Sierra Research
Runtime: multi-turn
License: unknown
Size: v0.2.3
Published: Sep 2025
Canonical: app.primeintellect.ai/dashboard/environments/primeintellect/tau2-bench

Cite

Notes

Only stored in your browser.

Attribution

README: api.primeintellect.ai/api/v1/environmentshub/primeintellect/tau2-bench/@0.2.3/inspect

Lift evidence

Eval	Tools known to lift	Source paper
Tau2	TAU 2 Bench RL Env (Prime Intellect)	-

Same problem set, this tool's harness. Run it to score a model on the test.

Sierra

Sierra's dual-control extension of τ-bench - now the user is also an LLM and both agents share access to the same tool-driven environment.