Welcome to the repository for the paper titled "VoiceAgentEval: A Dual-Dimensional Benchmark for Expert-Level Intelligent Voice-Agent Evaluation of xbench's Professional-Aligned Series". Initiated by Meituan, and supported by the xbench Project Team, this work proposes VoiceAgentEval, a comprehensive benchmark for evaluating large language models (LLMs) in expert-level intelligent outbound ...
ign of agent work pipelines and from agents trained end-to-end in real-world environments. This paper focuses on the evaluation of vertical agents and the tracking of their productivity value scaling. We will continuously collect evaluation results for vertical agents to observe and track the characterist
Mark schemes should be read in conjunction with the question paper and the Principal Examiner Report for Teachers. Cambridge will not enter into discussions about these mark schemes.
READ THESE INSTRUCTIONS FIRST Write your Centre number, candidate number and name on all the work you hand in. Write in dark blue or black pen in the spaces provided on the Question Paper. You may use a soft pencil for any diagrams, graphs or rough working. Do not use staples, paper clips, highlighters, glue or correction fluid.
Paper 3 (Practical Test), maximum raw mark 40 This mark scheme is published as an aid to teachers and candidates, to indicate the requirements of the examination. It shows the basis on which Examiners were instructed to award marks. It does not indicate the details of the discussions that took place at an Examiners’ meeting before marking began, which would have considered the acceptability ...
Do not use staples, paper clips, highlighters, glue or correction fluid. DO NOT WRITE IN ANY BARCODES. Answer all questions. The businesses described in this question paper are entirely fictitious. At the end of the examination, fasten all your work securely together.