Skip to content
Review

Isolation as a First-Class Principle for LLM-Agent System Safety: Concepts, Taxonomy, Challenges and Future Directions

Jul 2026 · 0 citations · 154 references
Computer Science

TL;DR

This survey treats isolation as a first-class principle for LLM-agent system safety, and organizes the literature with a boundary-centric taxonomy of five boundaries: user-agent, agent-tool, agent-execution, agent-agent, and system-environment.

Abstract

The capability of LLM agents to function as the ``brain''of a system fundamentally expands the scope of analysis beyond a standalone model. Consequently, safety is no longer only about input--output content alignment. It also concerns system behavior and real-world execution outcomes. However, the current literature is fragmented across attack types, applications, and benchmarks. This makes it hard to explain why failures such as prompt injection, tool misuse, and memory poisoning often share the same structural cause, and how they spread through an agent workflow. In this survey, we treat isolation as a first-class principle for LLM-agent system safety. By isolation, we refer to the separation of user inputs, tool access, execution channels, inter-agent communication, and environment-originated context. We organize the literature with a boundary-centric taxonomy of five boundaries: user-agent, agent-tool, agent-execution, agent-agent, and system-environment. This view helps identify where the loss of isolation first occurs, how compromise propagates across boundaries, and which defenses are most relevant at each interface. We also summarize cross-boundary failure paths, discuss open challenges, and outline a research agenda for isolation-by-construction in future agent systems.

View source

Similar papers

Preprint Jul 2026

Agentao: A Policy-Governed Runtime Harness for Embeddable Tool-Using LLM Agents

Agentao is presented, a governed local-first runtime for tool-using LLM agents that separates model-generated action proposals from host-authorized execution through a layered architecture consisting of host-facing surfaces, a host contract, a runtime core, a permission-mediated tool system, and supporting subsystems for memory, replay, plugins, skills, sub-agents, and protocol integration.

Bo Jin, Q. Jiao, Xin Tong · 1 citation
Conference Jul 2026

Metamorphic Testing of Multi-Agent LLM Systems: A Trace-Based Behavioral Oracle Framework

Multi-agent systems built on large language models (LLMs) are increasingly deployed for complex tasks requiring autonomous planning, tool use, and inter-agent coordination. However, the non-deterministic nature of LLM outputs and the emergent behavior arising from agent interactions render traditional test oracles ineffective, creating a critical gap in quality assurance for agentic AI. This work introduces MORPHAGENT, a framework designed to address the oracle problem in multi-agent LLM systems through trace-based behavioral analysis. Our contributions are threefold: (1) goal-preservation relations that verify consistent goal achievement under input perturbations, (2) coordination-consistency relations that validate inter-agent delegation and communication patterns under agent substitution and reordering, and (3) tool-use integrity relations that ensure semantic equivalence of tool invocation sequences under prompt paraphrasing. MorphAgent instruments agent execution to capture structured traces comprising planning steps, tool calls, message exchanges, and final outputs, then systematically applies metamorphic transformations and checks behavioral invariants without requiring ground-truth oracles. We evaluate the framework on four multi-agent benchmarks spanning code generation, research synthesis, customer service, and data analysis tasks, encompassing 2,840 source-followup execution pairs across three LLM backends. Results show that MORPHAGENT detects 82.0% of seeded behavioral faults, including 90.3% of coordination failures and 81.7% of goal-deviation faults, while maintaining a false positive rate of 6.1%. The framework uncovers 14 previously unreported behavioral anomalies in established multi-agent frameworks, demonstrating its practical utility for assuring agentic AI reliability. These results suggest that trace-based metamorphic testing can serve as a practical foundation for reliable validation of emerging agentic AI systems.

Gopalakrishnan Marimuthu · 0 citations
Review Open access Aug 2026

From Language Models to Agentic AI: A Survey of Autonomous, Action-Enabled, and Collaborative LLM Agents

A unified, taxonomy-driven, and deployment-oriented survey of agentic AI systems, synthesizing recent advances through a modular reference architecture and a four-dimensional taxonomy that characterizes agents along the axes of autonomy, tool use, collaboration, and safety–governance is presented.

Sparsh Bajoria, Shreyanshu Ranjan, Adhitya M et al. · 0 citations
#small language model Preprint Aug 2026

The Evaluation Context Protocol (ECP): A Portable Contract for AI Agent Evaluation

This paper proposes the Evaluation Context Protocol (ECP), an early-stage, vendor-neutral framework intended to act as a portable evaluation contract layer for agentic systems and describes an open-source reference implementation that includes adapters for LangChain, LlamaIndex, CrewAI, and PydanticAI.

Aniket Wattamwar, Manav Anandani, Mrunal Kakirwar · 0 citations
#artificial intelligence Review Aug 2026

LLM-Based Agents for Software and Systems Security: Approaches, Applications, and Assessment

A systematic literature review of technical approaches, including agent architecture, perception, memory, reasoning and planning, action space, orchestration, and self-improvement, reveals a field that has built agents able to act but not yet agents whose authority is bounded or whose behavior is auditable.

Jing-Jing Nie, Jiawei Guo, Krishna Meda et al. · 0 citations
Preprint Aug 2026

Agent Gym: A Framework for Continuous Evaluation and Evolution of LLM Agents Through Human-in-the-Loop Feedback

Agent Gym is introduced, a modular, domain-agnostic framework that wraps any existing LLM-based agent in a continuous evaluation-and-evolution loop and introduces the Spec-to-Note Gap, an autoencoder-inspired view of agentic system transparency.

Pouya Ghiasnezhad Omran, Michael Zimmermann, Duncan Cambridge et al. · 0 citations