Benchmark
τ³-Bench
A benchmark for agent tool use and multi-turn interaction. This work uses its banking-domain instances to evaluate agent memory and routing performance.
Timeline (last 90 days)
Oct 30
The research team evaluated Routed CL on a heterogeneous task stream interleaving 301 instances from six CL-Bench tasks and 97 banking-domain instances from τ³-Bench; the experiments covered four language models and five matched rollouts were performed.
Unverified50%