{"id":"sierra-research-tau2-bench","title":"tau2-bench (customer-service agent benchmark)","type":"benchmark","industry":"customer-service","roles":["ecommerce-support"],"summary":"τ-bench family benchmark (MIT) that simulates user–agent conversations in customer-service domains (retail, airline, telecom, banking) with tools, policies and automatic task evaluation.","summary_lang":"en","source_url":"https://github.com/sierra-research/tau2-bench","raw_url":"https://raw.githubusercontent.com/SiinXu/agent-academy/main/data/originals/sierra-research-tau2-bench.md","upstream_raw_url":"https://raw.githubusercontent.com/sierra-research/tau2-bench/main/README.md","repo":"sierra-research/tau2-bench","author":"sierra-research","license":"MIT","redistributable":true,"content_policy":"mirror-with-attribution","original":{"kind":"full","license":"MIT","url":"https://github.com/sierra-research/tau2-bench"},"install":null,"security":{"audited":false,"executes_code":false,"needs_credentials":false,"writes_external":false},"metrics":{"repo_stars":null,"repo_pushed_at":null},"course_step":"5-self-check","status":"active","first_seen":"2026-10-15T10:15:30Z","updated_at":"2026-10-15T10:15:30Z","checked_at":"2026-10-15T10:15:30Z","http_status":{"source":200},"page":"https://academy.incidental.site/r/sierra-research-tau2-bench/","source":"seed"}