Act While Thinking: Accelerating LLM Agents via Pattern-Aware Speculative Tool Execution
AI 摘要
PASTE通过预测工具调用模式，进行推测性工具执行，显著加速了LLM Agent的任务完成。
主要贡献
- 提出了Pattern-Aware Speculative Tool Execution (PASTE)方法。
- 通过推测性执行隐藏工具延迟，提升Agent性能。
- 实验证明PASTE能显著减少任务完成时间和提高工具执行吞吐量。
方法论
PASTE通过分析Agent的工具调用序列和数据依赖性，预测下一步工具调用，进行推测性执行。
原文摘要
LLM-powered agents are emerging as a dominant paradigm for autonomous task solving. Unlike standard inference workloads, agents operate in a strictly serial "LLM-tool" loop, where the LLM must wait for external tool execution at every step. This execution model introduces severe latency bottlenecks. To address this problem, we propose PASTE, a Pattern-Aware Speculative Tool Execution method designed to hide tool latency through speculation. PASTE is based on the insight that although agent requests are semantically diverse, they exhibit stable application level control flows (recurring tool-call sequences) and predictable data dependencies (parameter passing between tools). By exploiting these properties, PASTE improves agent serving performance through speculative tool execution. Experimental results against state of the art baselines show that PASTE reduces average task completion time by 48.5% and improves tool execution throughput by 1.8x.