AI Paper Atlas

Research map / Large language models / Agents, code and math

A Theory of Adaptive Scaffolding for LLM-Based Pedagogical Agents

Clayton Cohn, Surya Rayala, Namrata Srivastava, Joyce Horn Fonteles, Shruti Jain, Xinying Luo, Divya Mereddy, Naveeduddin Mohammed, Gautam Biswas

AAAI 2026 · Large language models › Agents, code and math · approach: Long-horizon LLM agents · 29 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add chain-of-thought explanations to few-shot examples (ablation)Inquizzitor GPT-4o grader · FA2 scoringweighted kappa: 93.58 -> 96.03Improved
add chain-of-thought explanations to few-shot examples (ablation)Inquizzitor GPT-4o grader · FA3 scoringweighted kappa: 94.45 -> 96.12Improved
add two few-shot examples without explanations to I/O prompt (ablation)Inquizzitor GPT-4o grader · FA4 scoringweighted kappa: 89.73 -> 80.69Hurt
add few-shot examples without explanations to I/O prompt (ablation)Inquizzitor GPT-4o grader · FA2 scoringweighted kappa: 91.28 -> 93.58Improved
add chain-of-thought explanations to few-shot examples (ablation)Inquizzitor GPT-4o grader · FA4 scoringweighted kappa: 80.69 -> 84.91Improved
add active learning prompt revisions after CoT (ablation)Inquizzitor GPT-4o grader · FA4 scoringweighted kappa: 84.91 -> 90.61Improved
full prompt pipeline versus plain I/O prompt (ablation)Inquizzitor GPT-4o grader · FA4 scoringweighted kappa: 89.73 -> 90.61No clear effect
add CoT to few-shot examples (ablation)Inquizzitor GPT-4o grader · FA4 scoringmicro-F1: 78.00 -> 78.00No clear effect
add ICL examples to I/O prompt (ablation)Inquizzitor GPT-4o grader · FA4 scoringmicro-F1: 82.00 -> 78.00Hurt
prompt agent with goal-setting construct instructionsInquizzitor · student conversationsgoal-setting faithfulness: 28.59 -> 18.36 (FA2 to FA4); unfaithfulness 53.38 -> 56.87Hurt
prompt agent with ZPD and self-efficacy construct instructionsInquizzitor · student conversationsZPD faithfulness: 59.26 (FA2), 65.88 (FA3), 62.20 (FA4)Improved
instruct agent to resist score change requestsInquizzitor · student conversationsscore changes: fewer than 1% of casesImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy