发表机构
Google LLC; Purdue University（谷歌公司; 普渡大学）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
针对现有智能体运行时的长程延迟与上下文污染问题，提出SKILL.state架构，用显式可变执行状态替代追加式对话历史，提升任务准确率并降低令牌消耗。
AI 中文摘要
大型语言模型（LLMs）日益成为执行复杂、长时程程序性技能的自主智能体。现有智能体运行时通过持续将观测、动作和中间推理轨迹追加到不断增长的对话历史中来维持执行，这会在长时程中导致延迟下降和上下文污染故障。我们提出SKILL.state，一种运行时架构，它用显式、可变的执行状态取代仅追加的对话历史。在每个执行步骤，模型仅接收不可变的技能规范、当前结构化执行状态和最新观测。中间推理在生成经验证的状态更新后立即丢弃，防止执行历史导致的提示增长。在不同数据集、模型和执行环境中，SKILL.state提升了任务准确性，同时大幅减少了累计令牌消耗。我们的结果表明，显式执行状态是一种适用于可扩展长程智能体技能的有效且架构无关的抽象。
英文摘要
Large Language Models (LLMs) increasingly act as autonomous agents executing complex, long-running procedural skills. Existing agent runtimes maintain execution by continually appending observations, actions, and intermediate reasoning traces to an ever-growing conversation history, causing latency degradation and context-poisoning failures over long horizons. We present SKILL. state, a runtime architecture that replaces append-only conversational history with an explicit, mutable execution state. At each execution step, the model receives only the immutable skill specification, the current structured execution state, and the latest observation. Intermediate reasoning is discarded immediately after producing a validated state update, preventing prompt growth with execution history. Across diverse datasets, models, and execution environments, SKILL. state improves task accuracy while substantially reducing cumulative token consumption. Our results demonstrate that explicit execution state is an effective and architecture-agnostic abstraction for scalable long-horizon agent skills.
Commentsaccepted at EMNLP
