CURIOBOT curiosity-modulated tutoring framework¶
Product or Programme · All products and programmes
Evidence · 2 claims (2 for) · 1 study (1 causal),q2· 0 of 1 report an effect size · 2 claims rest on one study
Description¶
CURIOBOT is a Ganganath et al. research-developed inference-time prompting framework that uses an LLM modulator and curiosity-conditioned conversational operators to guide tutoring dialogue.
Components¶
Claims¶
- Curiosity-oriented linguistic interventions via CURIOBOT consistently improve all learner-side exploratory dimensions relative to baseline LLM tutoring across model families [+M]
- CONFLICT operator achieves the highest downstream success rate among Berlyne-inspired curiosity operators, while NOVELTY is selected most frequently with a substantially lower success rate [+M]
Related Products and Programmes¶
-
Key Sources¶
- Ganganath, G., Bolonghege, P., Lyu, Q., Varakantham, P., & Kandappu, T. (2026). Curiosity as Linguistic Intervention: Using LLM Tutoring Dialogues to Influence Exploratory Learning Behavior. https://arxiv.org/abs/2606.22349. doi:10.48550/arxiv.2606.22349
Page metadata
| Field | Value |
|---|---|
type |
product |
id |
curiobot-curiosity-modulated-tutoring-framework |
title |
CURIOBOT curiosity-modulated tutoring framework |
description |
CURIOBOT is a Ganganath et al. |
status |
review |
product_kind |
framework |
generated |
by process:settle-candidates on 2026-10-10 |
trust |
unverified — no one has confirmed this page's content |
Frontmatter is the page's machine-readable record — see the Schema & Guide.