mlsanityData to 7 Oct 2026

Evidence-Decision-Feedback: Theory-Driven Adaptive Scaffolding for LLM Agents

arXiv 2602.01415 ↗First posted 1 Feb 2026cs.MAcited by 2

On the map: LLM agents and tool use → Educational agents and math problem solving

Abstract (arXiv)

LLMs offer tremendous opportunities for pedagogical agents to help students construct knowledge and develop problem-solving skills, yet many of these agents operate on a "one-size-fits-all" basis, limiting their ability to personalize support. To address this, we introduce Evidence-Decision-Feedback (EDF), a theoretical framework for adaptive scaffolding with LLM agents. EDF integrates elements of intelligent tutoring systems (ITS) and agentic behavior by organizing interactions around evidentiary inference, pedagogical decision-making, and adaptive feedback. We instantiate EDF through Copa, a Collaborative Peer Agent for STEM+C problem-solving. In an authentic high school classroom study, we show that EDF-guided interactions align feedback with students' demonstrated understanding and task mastery; promote scaffold fading; and support interpretable, evidence-grounded explanations without fostering overreliance.

Key facts. Cited by 2 papers in the map (data through 7 Oct 2026). Placed in Educational agents and math problem solving, one of 16 directions in LLM agents and tool use. Builds on 13 of its 41 references that are in the map. First posted on arXiv 1 Feb 2026.

Builds on

13 of 41 references.

Closest ancestors · 2

Same direction, newest first

  1. 2025A Theory of Adaptive Scaffolding for LLM-Based Pedagogical Agents2 Aug
  2. 2025Personalizing Student-Agent Interactions Using Log-Contextualized Retrieval-Augmented Generation (RAG)22 May

Other references · 11

  1. 2025Your Brain on ChatGPT: Accumulation of Cognitive Debt when Using an AI Assistant for Essay Writing Taskcited by 103
  2. 2024Towards Responsible Development of Generative AI for Education: An Evaluation-Driven Approachcited by 53
  3. 2024Enhancing LLM-Based Feedback: Insights from Intelligent Tutoring Systems and the Learning Sciencescited by 37
  4. 2025Measuring Agents in Productioncited by 35
  5. 2024A Chain-of-Thought Prompting Approach with LLMs for Evaluating Students' Formative Assessment Responses in Sciencecited by 31
  6. 2025Adaptation of Agentic AI: A Survey of Post-Training, Memory, and Skillscited by 19
  7. 2025Can Large Language Models Match Tutoring System Adaptivity? A Benchmarking Studycited by 17
  8. 2024A LLM-Powered Automatic Grading Framework with Human-Level Guidelines Optimizationcited by 16
  9. 2024Towards A Human-in-the-Loop LLM Approach to Collaborative Discourse Analysiscited by 7
  10. 2025CoTAL: Human-in-the-Loop Prompt Engineering for Generalizable Formative Assessment Scoring and Feedbackcited by 4
  11. 2025LLM-Generated Feedback Supports Learning If Learners Choose to Use Itcited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Read the Paper, Write the Code: Agentic Reproduction of Social-Science Resultscited by 5
  2. 2026BEAGLE: Behavior-Enforced Agent for Grounded Learner Emulationcited by 1

Similar, not cited

Close in wording, no citation either way

  1. 2026A Theory-Guided LLM Pedagogical Agent for STEM+C Scaffolding Without Over-Reliance
  2. 2026Confirming Correct, Missing the Rest: LLM Tutoring Agents Struggle Where Feedback Matters Most
  3. 2026Enhancing LLM Problem Solving via Tutor-Student Multi-Agent Interaction
  4. 2026AgentSchool: An LLM-Powered Multi-Agent Simulation for Education
  5. 2026REFINE: Real-world Exploration of Interactive Feedback and Student Behaviour
  6. 2026Tailoring Scaffolding to Diagnostic Strategies: Theory-Informed LLM-Based Agents
  7. 2025Towards Adaptive Feedback with AI: Comparing the Feedback Quality of LLMs and Teachers on Experimentation Protocols
  8. 2025IntelliCode: A Multi-Agent LLM Tutoring System with Centralized Learner Modeling