ALTK-Evolve: learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model
Read the original at huggingface.co→Original headline: "ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model"
Coverage timeline
- Oct 20, 15:19 UTC Hugging Face lead source ALTK-Evolve: How learned memory tops the τ²-bench leaderboard on customer service tasks without a frontier model