𝜏-bench: benchmarking AI agents for the real-world

Sierra’s AI research team is on a mission to advance the frontier of conversational AI agents. In this research paper, we present a new benchmark for evaluating AI agents' performance and reliability in real-world settings, with dynamic user and tool interaction.

Download

View more resources

𝜏²-bench: evaluating conversational agents in a dual-control environment

𝜏²-bench challenges AI agents not just to reason and act, but to coordinate, guide, and assist a user in achieving a shared objective. This leap from solo operation to co-ownership of a task pushes agents into a much more demanding space.

June 11, 2025

See what Sierra can do for you

Find out how Sierra can help your business build better, more human customer experiences with AI.

Learn more