# PolicyMem: Geometric Policy Memory for LLM Governance

arXiv: https://arxiv.org/abs/2609.13734 · HTML: https://mlsanity.com/paper/2609.13734/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 12 Sep 2026.

## Builds on (most cited first, 22 of 22)

- [The Llama 3 Herd of Models](https://mlsanity.com/paper/2407.21783/) (2024)
- [Qwen3 Technical Report](https://mlsanity.com/paper/2505.09388/) (2025)
- [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://mlsanity.com/paper/2305.18290/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Llama Guard: LLM-based Input-Output Safeguard for Human-AI Conversations](https://mlsanity.com/paper/2312.06674/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [BeaverTails: Towards Improved Safety Alignment of LLM via a Human-Preference Dataset](https://mlsanity.com/paper/2307.04657/) (2023)
- [Evaluating Very Long-Term Conversational Memory of LLM Agents](https://mlsanity.com/paper/2402.17753/) (2024)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [WildGuard: Open One-Stop Moderation Tools for Safety Risks, Jailbreaks, and Refusals of LLMs](https://mlsanity.com/paper/2406.18495/) (2024)
- [NeMo Guardrails: A Toolkit for Controllable and Safe LLM Applications with Programmable Rails](https://mlsanity.com/paper/2310.10501/) (2023)
- [A Holistic Approach to Undesired Content Detection in the Real World](https://mlsanity.com/paper/2208.03274/) (2022)
- [Qwen3Guard Technical Report](https://mlsanity.com/paper/2510.14276/) (2025)
- [AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts](https://mlsanity.com/paper/2404.05993/) (2024)
- [Evo-Memory: Benchmarking LLM Agent Test-time Learning with Self-Evolving Memory](https://mlsanity.com/paper/2511.20857/) (2025)
- [Aegis2.0: A Diverse AI Safety Dataset and Risks Taxonomy for Alignment of LLM Guardrails](https://mlsanity.com/paper/2501.09004/) (2025)
- [GuardReasoner: Towards Reasoning-based LLM Safeguards](https://mlsanity.com/paper/2501.18492/) (2025)
- [Externalization in LLM Agents: A Unified Review of Memory, Skills, Protocols and Harness Engineering](https://mlsanity.com/paper/2604.08224/) (2026)
- [Exponential Moving Average of Weights in Deep Learning: Dynamics and Benefits](https://mlsanity.com/paper/2411.18704/) (2024)
- [Mem-Gallery: Benchmarking Multimodal Long-Term Conversational Memory for MLLM Agents](https://mlsanity.com/paper/2601.03515/) (2026)
- [Dynamic Content Moderation in Livestreams: Combining Supervised Classification with MLLM-Boosted Similarity Matching](https://mlsanity.com/paper/2512.03553/) (2025)
- [RAR: Setting Knowledge Tripwires for Retrieval Augmented Rejection](https://mlsanity.com/paper/2505.13581/) (2025)

## Abstract (arXiv)

As large language models (LLMs) are increasingly deployed in real-world high-stakes applications, effective governance has become essential. Existing safeguards largely follow two paradigms: learning-based guards provide strong semantic discrimination but couple policy behavior to trained models and taxonomies, while programmable frameworks offer flexible control but require substantial manual prompt and workflow engineering. Neither externalizes policies as reusable operational states, making it difficult to consistently reuse policy evidence across detection, intervention, and verification. In this paper, we introduce PolicyMem, a geometric policy memory that externalizes natural-language policies as reusable geometric memory objects represented by low-rank subspaces in a shared representation space. A memory writer compiles natural-language policies into policy memory slots, and query-response pairs read the policy memory through projection energy. The resulting policy-evidence profile directly mediates the safety verdict and is reused for policy attribution and post-intervention verification. Coupled with a response rewriter, PolicyMem enables a detect-rewrite-verify loop for LLM governance. Across five widely used benchmarks, PolicyMem achieves state-of-the-art unsafe behavior detection while enabling effective policy attribution, rewriting, and post-intervention verification through the shared policy memory.