Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations

• URL: http://arxiv.org/abs/2509.08646v1
• Date: Wed, 10 Sep 2025 14:41:07 GMT
• Title: Architecting Resilient LLM Agents: A Guide to Secure Plan-then-Execute Implementations
• Authors: Ron F. Del Rosario, Klaudia Krawiecka, Christian Schroeder de Witt,
• Abstract summary: This paper provides a guide to the Plan-then-Execute'' (P-t-E) pattern, an agentic design that separates strategic planning from tactical execution.<n>A central focus is placed on the security implications of this design, particularly its inherent resilience to indirect prompt injection attacks.<n>To make these principles actionable, this guide provides detailed implementation blueprints and working code references for three leading agentic frameworks.
• Score: 0.8078139482203387
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: As Large Language Model (LLM) agents become increasingly capable of automating complex, multi-step tasks, the need for robust, secure, and predictable architectural patterns is paramount. This paper provides a comprehensive guide to the ``Plan-then-Execute'' (P-t-E) pattern, an agentic design that separates strategic planning from tactical execution. We explore the foundational principles of P-t-E, detailing its core components - the Planner and the Executor - and its architectural advantages in predictability, cost-efficiency, and reasoning quality over reactive patterns like ReAct (Reason + Act). A central focus is placed on the security implications of this design, particularly its inherent resilience to indirect prompt injection attacks by establishing control-flow integrity. We argue that while P-t-E provides a strong foundation, a defense-in-depth strategy is necessary, and we detail essential complementary controls such as the Principle of Least Privilege, task-scoped tool access, and sandboxed code execution. To make these principles actionable, this guide provides detailed implementation blueprints and working code references for three leading agentic frameworks: LangChain (via LangGraph), CrewAI, and AutoGen. Each framework's approach to implementing the P-t-E pattern is analyzed, highlighting unique features like LangGraph's stateful graphs for re-planning, CrewAI's declarative tool scoping for security, and AutoGen's built-in Docker sandboxing. Finally, we discuss advanced patterns, including dynamic re-planning loops, parallel execution with Directed Acyclic Graphs (DAGs), and the critical role of Human-in-the-Loop (HITL) verification, to offer a complete strategic blueprint for architects, developers, and security engineers aiming to build production-grade, resilient, and trustworthy LLM agents.

Related papers

• Zero-Shot Instruction Following in RL via Structured LTL Representations [50.41415009303967]
  We study instruction following in multi-task reinforcement learning, where an agent must zero-shot execute novel tasks not seen during training.<n>In this setting, linear temporal logic has recently been adopted as a powerful framework for specifying structured, temporally extended tasks.<n>While existing approaches successfully train generalist policies, they often struggle to effectively capture the rich logical and temporal structure inherent in specifications.
  arXiv  Detail & Related papers  (2026-02-15T23:22:50Z)
• TodoEvolve: Learning to Architect Agent Planning Systems [68.48983335970901]
  TodoEvolve is a meta-planning paradigm that autonomously synthesizes and dynamically revises task-specific planning.<n>PlanFactory provides a common interface for heterogeneous planning patterns.<n>TodoEvolve consistently surpasses carefully engineered planning modules while maintaining economical API costs and runtime overhead.
  arXiv  Detail & Related papers  (2026-02-08T06:37:01Z)
• PerfGuard: A Performance-Aware Agent for Visual Content Generation [53.591105729011595]
  PerfGuard is a performance-aware agent framework for visual content generation.<n>It integrates tool performance boundaries into task planning and scheduling.<n>It has advantages in tool selection accuracy, execution reliability, and alignment with user intent.
  arXiv  Detail & Related papers  (2026-01-30T05:12:19Z)
• Designing Domain-Specific Agents via Hierarchical Task Abstraction Mechanism [61.01709143437043]
  We introduce a novel agent design framework centered on a Hierarchical Task Abstraction Mechanism (HTAM)<n>Specifically, HTAM moves beyond emulating social roles, instead structuring multi-agent systems into a logical hierarchy that mirrors the intrinsic task-dependency graph of a given domain.<n>We instantiate this framework as EarthAgent, a multi-agent system tailored for complex geospatial analysis.
  arXiv  Detail & Related papers  (2025-11-21T12:25:47Z)
• Hierarchical Planning for Complex Tasks with Knowledge Graph-RAG and Symbolic Verification [5.727096041675994]
  Large Language Models (LLMs) have shown promise as robotic planners but often struggle with long-horizon and complex tasks.<n>We propose a neuro-symbolic approach that enhances LLMs-based planners with Knowledge Graph-based RAG for hierarchical plan generation.
  arXiv  Detail & Related papers  (2025-04-06T18:36:30Z)
• DHP: Discrete Hierarchical Planning for Hierarchical Reinforcement Learning Agents [2.1438108757511958]
  We propose a method that replaces continuous distance estimates with discrete reachability checks to evaluate subgoal feasibility.<n>Experiments in 25-room navigation environments demonstrate $100%$ success rate.<n>The method also generalizes to momentum-based control tasks and requires only $log N$ steps for replanning.
  arXiv  Detail & Related papers  (2025-02-04T03:05:55Z)
• Propose, Assess, Search: Harnessing LLMs for Goal-Oriented Planning in Instructional Videos [48.15438373870542]
  VidAssist is an integrated framework designed for zero/few-shot goal-oriented planning in instructional videos. It employs a breadth-first search algorithm for optimal plan generation. Experiments demonstrate that VidAssist offers a unified framework for different goal-oriented planning setups.
  arXiv  Detail & Related papers  (2024-09-30T17:57:28Z)
• Unlocking Reasoning Potential in Large Langauge Models by Scaling Code-form Planning [94.76546523689113]
  We introduce CodePlan, a framework that generates and follows textcode-form plans -- pseudocode that outlines high-level, structured reasoning processes. CodePlan effectively captures the rich semantics and control flows inherent to sophisticated reasoning tasks. It achieves a 25.1% relative improvement compared with directly generating responses.
  arXiv  Detail & Related papers  (2024-09-19T04:13:58Z)
• Swiss Cheese Model for AI Safety: A Taxonomy and Reference Architecture for Multi-Layered Guardrails of Foundation Model Based Agents [12.593620173835415]
  Foundation Model (FM)-based agents are revolutionizing application development across various domains.<n>We present a comprehensive taxonomy of runtime guardrails for FM-based agents to identify the key quality attributes for guardrails and design dimensions.<n>Inspired by the Swiss Cheese Model, we also propose a reference architecture for designing multi-layered runtime guardrails for FM-based agents.
  arXiv  Detail & Related papers  (2024-08-05T03:08:51Z)
• AgentGen: Enhancing Planning Abilities for Large Language Model based Agent via Environment and Task Generation [81.32722475387364]
  Large Language Model-based agents have garnered significant attention and are becoming increasingly popular.<n>Planning ability is a crucial component of an LLM-based agent, which generally entails achieving a desired goal from an initial state.<n>Recent studies have demonstrated that utilizing expert-level trajectory for instruction-tuning LLMs effectively enhances their planning capabilities.
  arXiv  Detail & Related papers  (2024-08-01T17:59:46Z)
• The Landscape of Emerging AI Agent Architectures for Reasoning, Planning, and Tool Calling: A Survey [0.0]
  This paper examines the recent advancements in AI agent implementations. It focuses on their ability to achieve complex goals that require enhanced reasoning, planning, and tool execution capabilities.
  arXiv  Detail & Related papers  (2024-04-17T17:32:41Z)
• Towards Responsible Generative AI: A Reference Architecture for Designing Foundation Model based Agents [28.406492378232695]
  Foundation model based agents derive their autonomy from the capabilities of foundation models. This paper presents a pattern-oriented reference architecture that serves as guidance when designing foundation model based agents.
  arXiv  Detail & Related papers  (2023-11-22T04:21:47Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.