# SafeHarbor: Defining Precise Decision Boundaries via Hierarchical Memory-Augmented Guardrail for LLM Agent Safety

arXiv: https://arxiv.org/abs/2605.05704 · HTML: https://mlsanity.com/paper/2605.05704/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Agent threats, guardrails and governance, one of 16 directions in LLM agents and tool use.
- Builds on 24 of its 31 references that are in the map.
- First posted on arXiv 7 May 2026.

## Placed in

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

## Builds on (most cited first, 24 of 24)

- [Retrieval-Augmented Generation for Knowledge-Intensive NLP Tasks](https://mlsanity.com/paper/2005.11401/) (2020)
- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Toolformer: Language Models Can Teach Themselves to Use Tools](https://mlsanity.com/paper/2302.04761/) (2023)
- [PaLM-E: An Embodied Multimodal Language Model](https://mlsanity.com/paper/2303.03378/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [SWE-agent: Agent-Computer Interfaces Enable Automated Software Engineering](https://mlsanity.com/paper/2405.15793/) (2024)
- [Jailbroken: How Does LLM Safety Training Fail?](https://mlsanity.com/paper/2307.02483/) (2023)
- [Not what you've signed up for: Compromising Real-World LLM-Integrated Applications with Indirect Prompt Injection](https://mlsanity.com/paper/2302.12173/) (2023)
- [Mind2Web: Towards a Generalist Agent for the Web](https://mlsanity.com/paper/2306.06070/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [A Survey on the Memory Mechanism of Large Language Model based Agents](https://mlsanity.com/paper/2404.13501/) (2024)
- [Identifying the Risks of LM Agents with an LM-Emulated Sandbox](https://mlsanity.com/paper/2309.15817/) (2023)
- [Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attacks](https://mlsanity.com/paper/2404.02151/) (2024)
- [AgentHarm: A Benchmark for Measuring Harmfulness of LLM Agents](https://mlsanity.com/paper/2410.09024/) (2024)
- [Agent-SafetyBench: Evaluating the Safety of LLM Agents](https://mlsanity.com/paper/2412.14470/) (2024)
- [ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory](https://mlsanity.com/paper/2509.25140/) (2025)
- [Scalable and Transferable Black-Box Jailbreaks for Language Models via Persona Modulation](https://mlsanity.com/paper/2311.03348/) (2023)
- [ShieldAgent: Shielding Agents via Verifiable Safety Policy Reasoning](https://mlsanity.com/paper/2503.22738/) (2025)
- [Optimization-based Prompt Injection Attack to LLM-as-a-Judge](https://mlsanity.com/paper/2403.17710/) (2024)
- [AGrail: A Lifelong Agent Guardrail with Effective and Adaptive Safety Detection](https://mlsanity.com/paper/2502.11448/) (2025)
- [Think-in-Memory: Recalling and Post-thinking Enable LLMs with Long-Term Memory](https://mlsanity.com/paper/2311.08719/) (2023)
- [Your Agent May Misevolve: Emergent Risks in Self-evolving LLM Agents](https://mlsanity.com/paper/2509.26354/) (2025)
- [AdvAgent: Controllable Blackbox Red-teaming on Web Agents](https://mlsanity.com/paper/2410.17401/) (2024)
- [AgentAlign: Navigating Safety Alignment in the Shift from Informative to Agentic Large Language Models](https://mlsanity.com/paper/2505.23020/) (2025)

## Built on by (most cited first, 4 of 4)

- [SHE: Trajectory-driven Safety Harness Evolution for LLM Agents](https://mlsanity.com/paper/2608.09885/) (2026)
- [StepGuard: Learning Step-Level Guardrails with Scalable Supervision and Safety-Utility Balancing](https://mlsanity.com/paper/2608.24777/) (2026)
- [APPA: Recoverable Information-Flow Control for Real-World LLM Agents](https://mlsanity.com/paper/2607.24625/) (2026)
- [Yesterday's Shield, Today's Spear: A Self-Evolving Safety Guardrail in Production](https://mlsanity.com/paper/2608.08471/) (2026)

## Abstract (arXiv)

Recent advances in foundation models have transformed LLMs from passive conversational systems into autonomous agents capable of reasoning and tool execution. While these capabilities unlock substantial practical value, they also introduce new security risks, as adversaries can manipulate agents into performing harmful actions in real-world environments. Existing defense strategies mitigate such threats but frequently struggle to balance safety and utility, resulting in over-refusal of benign user requests. To mitigate this trade-off, we propose SafeHarbor, a novel framework designed to establish precise decision boundaries for LLM agents. Unlike static guidelines, SafeHarbor extracts context-aware defense rules through enhanced adversarial generation. We design a local hierarchical memory system for dynamic rule injection, offering a training-free, efficient, and plug-and-play solution. Furthermore, we introduce an information entropy-based self-evolution mechanism that continuously optimizes the memory structure through dynamic node splitting and merging. Extensive experiments demonstrate that SafeHarbor achieves state-of-the-art performance on both ambiguous benign tasks and explicit malicious attacks, notably attaining a peak benign utility of 63.6% on GPT-4o while maintaining a robust refusal rate exceeding 93% against harmful requests. The source code is publicly available at https://github.com/ljj-cyber/SafeHarbor.