Pith. sign in

REVIEW 8 cited by

Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise

Not yet reviewed by Pith; the record is open.

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2410.03017 v2 pith:X5PSIEQ4 submitted 2024-10-03 cs.CL

Tutor CoPilot: A Human-AI Approach for Scaling Real-Time Expertise

classification cs.CL
keywords tutorcopilottutorsstudentseducationhuman-aiaccessfind
verification ladder T0 review T1 audit T2 compute T3 formal T4 reserved
0 comments
read the original abstract

Generative AI, particularly Language Models (LMs), has the potential to transform real-world domains with societal impact, particularly where access to experts is limited. For example, in education, training novice educators with expert guidance is important for effectiveness but expensive, creating significant barriers to improving education quality at scale. This challenge disproportionately harms students from under-served communities, who stand to gain the most from high-quality education. We introduce Tutor CoPilot, a novel Human-AI approach that leverages a model of expert thinking to provide expert-like guidance to tutors as they tutor. This study is the first randomized controlled trial of a Human-AI system in live tutoring, involving 900 tutors and 1,800 K-12 students from historically under-served communities. Following a preregistered analysis plan, we find that students working with tutors that have access to Tutor CoPilot are 4 percentage points (p.p.) more likely to master topics (p<0.01). Notably, students of lower-rated tutors experienced the greatest benefit, improving mastery by 9 p.p. We find that Tutor CoPilot costs only $20 per-tutor annually. We analyze 550,000+ messages using classifiers to identify pedagogical strategies, and find that tutors with access to Tutor CoPilot are more likely to use high-quality strategies to foster student understanding (e.g., asking guiding questions) and less likely to give away the answer to the student. Tutor interviews highlight how Tutor CoPilot's guidance helps tutors to respond to student needs, though they flag issues in Tutor CoPilot, such as generating suggestions that are not grade-level appropriate. Altogether, our study of Tutor CoPilot demonstrates how Human-AI systems can scale expertise in real-world domains, bridge gaps in skills and create a future where high-quality education is accessible to all students.

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Forward citations

Cited by 8 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score.

  1. AI Assistance for Discretionary Work: Increasing Feedback Provision in Higher Education

    cs.HC 2026-06 accept novelty 7.0

    Randomized experiment finds AI draft assistance raises feedback provision by teaching assistants 10.8 percentage points without harming quality.

  2. Experimental Evidence on the Learning Impact of Generative AI

    econ.GN 2026-07 conditional novelty 6.5

    Off-the-shelf generative AI access raises student knowledge-test scores by 0.27 SD immediately and one week later, with delayed unaided essay gains concentrated among students who use AI to explain concepts rather tha...

  3. Conversational Human Audio-visual Talking Dialogue Generation

    cs.CV 2026-07 conditional novelty 6.0

    CHAT generates mutually responsive dyadic audio-visual dialogue clips from a single text prompt and yields a 50k synthetic pre-training set that improves facial reaction models on REACT 2024.

  4. CourseBlueprint: A Structured Pipeline for Adaptive Pedagogical Video Generation Grounded in Course Corpora

    cs.CY 2026-05 unverdicted novelty 6.0

    CourseBlueprint builds a typed pipeline over a 23-lecture biomedical imaging corpus to generate prerequisite-aware, learner-adaptive videos with auditable engagement contracts and slide grounding.

  5. Alignment has a Fantasia Problem

    cs.AI 2026-04 unverdicted novelty 6.0

    AI alignment must move beyond assuming users have fully formed goals and instead provide active cognitive support to help form and refine intent over time.

  6. Human Thinking under Plural LLM Assistance: Mathematical Problem Solving and Open-Ended Writing

    cs.HC 2026-04 unverdicted novelty 6.0

    Two controlled experiments show multi-agent LLM configurations with both tutors and peers deliver higher learning gains and less homogeneous outputs than single-LLM tutoring in math problem-solving and essay writing.

  7. Human Thinking under Plural LLM Assistance: Mathematical Problem Solving and Open-Ended Writing

    cs.HC 2026-04 unverdicted novelty 5.0

    Plural LLM setups (expert+peer in math; role-specialized pair in writing) improve post-task math performance and preserve writing idea diversity better than single-assistant or no-AI baselines.

  8. AI-Driven Assessment of Human Tutors: Linking Training Performance to Real-Life Practice

    cs.CY 2026-06 unverdicted novelty 4.0

    AI scoring of training and real-life transcripts from 86 tutors shows training performance predicts real tutoring quality with 0.25 SD effect size using mixed-effects models.