# SCRIBE: Structured Chain Reasoning for Interactive Behaviour Explanations using Tool Calling

arXiv: https://arxiv.org/abs/2510.26322 · HTML: https://mlsanity.com/paper/2510.26322/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- Placed in Reasoning benchmarks and evaluation, one of 17 directions in LLM reasoning.
- Builds on 7 of its 75 references that are in the map.
- First posted on arXiv 30 Oct 2025.

## Placed in

- LLM reasoning / [Reasoning benchmarks and evaluation](https://mlsanity.com/lr/reasoning-benchmarks-and-evaluation/)
- LLM agents and tool use / [Tool learning and function calling](https://mlsanity.com/agents/tool-learning-and-function-calling/)

## Builds on (most cited first, 7 of 7)

- [Sentence-BERT: Sentence Embeddings using Siamese BERT-Networks](https://mlsanity.com/paper/1908.10084/) (2019)
- [GPT-4o System Card](https://mlsanity.com/paper/2410.21276/) (2024)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [C-Pack: Packed Resources For General Chinese Embeddings](https://mlsanity.com/paper/2309.07597/) (2023)
- [Towards Modeling Learner Performance with Large Language Models](https://mlsanity.com/paper/2403.14661/) (2024)
- [DIVA: A Dirichlet Process Mixtures Based Incremental Deep Clustering Algorithm via Variational Auto-Encoder](https://mlsanity.com/paper/2305.14067/) (2023)
- [iLLuMinaTE: An LLM-XAI Framework Leveraging Social Science Explanation Theories Towards Actionable Student Performance Feedback](https://mlsanity.com/paper/2409.08027/) (2024)

## Built on by (most cited first, 3 of 3)

- [Evaluating Answer Leakage Robustness of LLM Tutors against Adversarial Student Attacks](https://mlsanity.com/paper/2604.18660/) (2026)
- [REFINE: Real-world Exploration of Interactive Feedback and Student Behaviour](https://mlsanity.com/paper/2603.29142/) (2026)
- [PIVOT: Preference-based Intervention Vectors for Pedagogical Tutor Steering](https://mlsanity.com/paper/2608.07509/) (2026)

## Abstract (arXiv)

Language models can be used to provide interactive, personalized student feedback in educational settings. However, real-world deployment faces three key challenges: privacy concerns, limited computational resources, and the need for pedagogically valid responses. These constraints require small, open-source models that can run locally and reliably ground their outputs in correct information. We introduce SCRIBE, a framework for multi-hop, tool-augmented reasoning designed to generate valid responses to student questions about feedback reports. SCRIBE combines domain-specific tools with a self-reflective inference pipeline that supports iterative reasoning, tool use, and error recovery. We distil these capabilities into 3B and 8B models via two-stage LoRA fine-tuning on synthetic GPT-4o-generated data. Evaluation with a human-aligned GPT-Judge and a user study with 108 students shows that 8B-SCRIBE models achieve comparable or superior quality to much larger models in key dimensions such as relevance and actionability, while being perceived on par with GPT-4o and Llama-3.3 70B by students. These findings demonstrate the viability of SCRIBE for low-resource, privacy-sensitive educational applications.