用预测动作并行执行，让智能体运行快20%且不丢精度。
Speculative Actions: A Lossless Framework for Faster Agentic Systems
- 用快速模型预判下一步动作并提前执行，只在匹配时确认。
- 在多场景下预测准确率达55%，最高降低20%延迟。
- 可灵活控制预测范围，避免成本飙升，适合实际部署。
AI智能体在复杂交互环境中应用日益广泛，但其运行延迟仍是训练、评估和真实使用中的主要瓶颈。传统智能体行为按顺序执行，每一步动作需调用API，可能带来显著延迟。例如，两个顶尖智能体下棋可能耗时数小时。本文提出Speculative Actions，一种通用的无损加速框架，灵感来自微处理器的推测执行和大模型推理中的推测解码。该方法利用快速模型预测未来可能的动作，并并行执行；仅当预测与实际结果一致时才提交。我们在游戏、电商和网页搜索场景中评估该方法，并在操作系统场景中研究其损失版扩展。实验显示，最多可实现55%的下一步动作预测准确率，带来最高20%的延迟降低。最后，我们提出了一个成本-延迟分析模型，形式化了推测宽度与节省时间之间的权衡，支持合理调参和选择性分支启动，确保多分支推测在不导致成本激增的前提下获得实际加速效果。
原文摘要 · Abstract (English)
AI agents are increasingly deployed in complex, interactive environments, yet their runtime remains a major bottleneck for training, evaluation, and real-world use. Typical agent behavior unfolds sequentially, with each action requiring an API call that can incur substantial latency. For example, a game of chess between two state-of-the-art agents can take hours. We introduce Speculative Actions, a lossless acceleration framework for general agentic systems. Inspired by speculative execution in microprocessors and speculative decoding in LLM inference, our method uses faster models to predict likely future actions and execute them in parallel, committing only when predictions match. We evaluate speculative actions across gaming, e-commerce, and web search environments, and additionally study a lossy extension in an operating systems setting. Across domains, we achieve up to 55% next-action prediction accuracy, translating into up to 20% latency reductions. Finally, we present a cost-latency analysis that formalizes the tradeoff between speculative breadth and time savings. This analysis enables principled tuning and selective branch launching to ensure that multi-branch speculation delivers practical speedups without prohibitive cost growth.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。