Tool-calling autonomous agents based on large language models using ReAct exhibit three limitations: serial latency, quadratic context growth, and vulnerability to prompt injection and hallucination. Recent work moves towards separating planning from execution but in each case the model remains coupled to the execution mechanics. We introduce a system-level abstraction for LLM agents which decouples the execution of agent workflows from the LLM reasoning layer. We define two first-class abstractions: (1) Intent-Gated Execution (IGX), a security paradigm that enforces intent at execution, and (2) an Executive Kernel that manages scheduling, tool dispatch, dependency resolution, failures and security. In KAIJU, the LLM plans upfront, optimistically scheduling tools in parallel with dependency-aware parameter injection. Tools are authorised via IGX based on four independent variables: scope, intent, impact, and clearance (external approval). KAIJU supports three adaptive execution modes (Reflect, nReflect, and Orchestrator), providing progressively finer-grained execution control apt for complex investigation and deep analysis or research. Empirical evaluation against a ReAct baseline shows that KAIJU has a latency penalty on simple queries due to planning overhead, convergence at moderate complexity, and a structural advantage on computational queries requiring parallel data gathering. Beyond latency, the separation enforces behavioural guarantees that ReAct cannot match through prompting alone. Code available at https://github.com/compdeep/kaiju

翻译：基于大型语言模型且使用ReAct模式的工具调用自主代理存在三个局限性：串行延迟、上下文呈二次增长，以及对提示注入和幻觉的脆弱性。近期研究倾向于将规划与执行分离，但每种方案中模型仍与执行机制耦合。我们提出了一种针对LLM代理的系统级抽象，将代理工作流的执行与LLM推理层解耦。我们定义了两种一级抽象：(1) 意图门控执行（IGX），一种在执行时强制实施意图的安全范式；(2) 内核执行器，负责管理调度、工具分发、依赖解析、故障处理与安全。在KAIJU中，LLM预先进行规划，以乐观态度并行调度工具，并注入参数至依赖图中。工具通过IGX基于四个独立变量获得授权：范围、意图、影响与许可（外部审批）。KAIJU支持三种自适应执行模式（Reflect、nReflect与Orchestrator），为复杂调查、深度分析或研究提供渐进细粒度的执行控制。与ReAct基线的实证评估表明，KAIJU在简单查询上因规划开销存在延迟惩罚，在中度复杂度查询时收敛，并在需要并行数据采集的计算型查询中具备结构性优势。除延迟表现外，这种分离机制强制了ReAct仅凭提示无法达成的行为保证。代码开源地址：https://github.com/compdeep/kaiju