Saved in:
Bibliographic Details
Main Authors: Ipeirotis, Panos, Rizakos, Konstantinos
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2603.18221
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866917498231717888
author Ipeirotis, Panos
Rizakos, Konstantinos
author_facet Ipeirotis, Panos
Rizakos, Konstantinos
contents Students in our AI/ML course submitted polished, well-argued project analyses. Then, in class discussion, we asked them to walk through a single choice from their own work. Many could not. The writing looked great. The understanding often wasn't. Oral examinations retain an evidentiary link where written work no longer does: a student who can reason aloud, defend a decision under follow-up, and adapt when pushed demonstrates something no submitted document can certify. The obstacle has always been cost. A 25-minute oral reviewed by two graders takes roughly 30 combined instructor and TA hours for 36 students; at 100 the format is untenable. Voice AI and automated grading change the arithmetic. We built Viva, a system that conducts a personalized oral exam, then grades the transcript with a panel of three LLMs that score independently, read each other's assessments, and revise. Across two undergraduate cohorts at NYU Stern (36 students in Fall 2025, 37 in Spring 2026), grading-LLM cost stayed under one dollar per exam within the ElevenLabs subscription covering our voice minutes; for deployments exceeding an equivalent credit pool, budget about a dollar per ten minutes of graded exam time, practical for weekly assignments, not just finals. The system also broke instructively: the agent asked several questions at once, failed to randomize topics across the cohort, and a voice cloned from the professor's came across as harsh, replaced in Spring 2026 with a calm preset. These failures, with an earlier finding that a monolithic agent handling both examination and grading proved unreliable, point to five candidate transferable patterns: decompose into single-purpose modules, constrain behavior with code rather than prompts, keep randomization out of the LLM, grade with a multi-model panel whose members disagree, and choose voice characteristics with the same care as question design.
format Preprint
id arxiv_https___arxiv_org_abs_2603_18221
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Scalable and Personalized Oral Assessments Using Voice AI
Ipeirotis, Panos
Rizakos, Konstantinos
Computers and Society
Students in our AI/ML course submitted polished, well-argued project analyses. Then, in class discussion, we asked them to walk through a single choice from their own work. Many could not. The writing looked great. The understanding often wasn't. Oral examinations retain an evidentiary link where written work no longer does: a student who can reason aloud, defend a decision under follow-up, and adapt when pushed demonstrates something no submitted document can certify. The obstacle has always been cost. A 25-minute oral reviewed by two graders takes roughly 30 combined instructor and TA hours for 36 students; at 100 the format is untenable. Voice AI and automated grading change the arithmetic. We built Viva, a system that conducts a personalized oral exam, then grades the transcript with a panel of three LLMs that score independently, read each other's assessments, and revise. Across two undergraduate cohorts at NYU Stern (36 students in Fall 2025, 37 in Spring 2026), grading-LLM cost stayed under one dollar per exam within the ElevenLabs subscription covering our voice minutes; for deployments exceeding an equivalent credit pool, budget about a dollar per ten minutes of graded exam time, practical for weekly assignments, not just finals. The system also broke instructively: the agent asked several questions at once, failed to randomize topics across the cohort, and a voice cloned from the professor's came across as harsh, replaced in Spring 2026 with a calm preset. These failures, with an earlier finding that a monolithic agent handling both examination and grading proved unreliable, point to five candidate transferable patterns: decompose into single-purpose modules, constrain behavior with code rather than prompts, keep randomization out of the LLM, grade with a multi-model panel whose members disagree, and choose voice characteristics with the same care as question design.
title Scalable and Personalized Oral Assessments Using Voice AI
topic Computers and Society
url https://arxiv.org/abs/2603.18221