News/$\tau$-Rec: A Verifiable Benchmark for Agentic R…
SatelightUnresolved

$\tau$-Rec: A Verifiable Benchmark for Agentic Recommender Systems

Read full release on Satelight
  • GPT-5.4
  • Claude Sonnet 4.6
  • Gemini 2.5 Flash
  • DeepSeek V4 Flash
  • Qwen3-32B
$\tau$-Rec: A Verifiable Benchmark for Agentic Recommender Systems