Honghua Dong

Honghua Dong is a Ph.D. candidate at the University of Toronto. His research focuses on the development and evaluation of language model agents. He is currently interning at Sierra, where he is working to improve language model agents in the domain of customer service.

Posts by Honghua Dong

𝜏²-bench: benchmarking agents in collaborative real-world scenarios

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. And, critically, it reflects the kinds of tasks AI agents are increasingly being asked to perform in the real world.

June 10, 2025

Honghua Dong

Posts by Honghua Dong

𝜏²-bench: benchmarking agents in collaborative real-world scenarios

See what Sierra can do for you.

Posts by Honghua Dong

𝜏²-bench: benchmarking agents in collaborative real-world scenarios