# SRPG: Semantically Reconstructed Privacy Guard for Zero-Trust Privacy in Educational Multi-Agent Systems

arXiv: https://arxiv.org/abs/2512.03694 · HTML: https://mlsanity.com/paper/2512.03694/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 7 of its 18 references that are in the map.
- First posted on arXiv 3 Dec 2025.

## Placed in

- LLM agents and tool use / [Agent threats, guardrails and governance](https://mlsanity.com/agents/agent-threats-guardrails-and-governance/)

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

- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Extracting Training Data from Large Language Models](https://mlsanity.com/paper/2012.07805/) (2020)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [What Does it Mean for a Language Model to Preserve Privacy?](https://mlsanity.com/paper/2202.05520/) (2022)
- [Privacy- and Utility-Preserving Textual Analysis via Calibrated Multivariate Perturbations](https://mlsanity.com/paper/1910.08902/) (2019)
- [Privacy-Enhancing Paradigms within Federated Multi-Agent Systems](https://mlsanity.com/paper/2503.08175/) (2025)

## Abstract (arXiv)

Multi-Agent Systems (MAS) with large language models (LLMs) enable personalized education but risk leaking minors personally identifiable information (PII) via unstructured dialogue. Existing privacy methods struggle to balance security and utility: role-based access control fails on unstructured text, while naive masking destroys pedagogical context. We propose SRPG, a privacy guard for educational MAS, using a Dual-Stream Reconstruction Mechanism: a strict sanitization stream ensures zero PII leakage, and a context reconstruction stream (LLM driven) recovers mathematical logic. This decouples instructional content from private data, preserving teaching efficacy. Tests on MathDial show SRPG works across models; with GPT-4o, it achieves 0.0000 Attack Success Rate (ASR) (zero leakage) and 0.8267 Exact Match, far outperforming the zero trust Pure LLM baseline (0.2138). SRPG effectively protects minors privacy without sacrificing mathematical instructional quality.