揭示网页交互式智能体效率瓶颈，提出缓存优化方案提升速度。
What Limits Agentic Systems Efficiency?
- 拆解系统延迟为API与网页环境两部分，定位性能瓶颈。
- 网页环境延迟最高占整体延迟53.7%，显著拖慢响应速度。
- 提出SpecCache缓存框架，缓存命中率提升58倍，延迟降低3.2倍。
大型语言模型（如OpenAI-o1和DeepSeek-R1）展现出强大的推理能力。为进一步提升模型表现，近期的智能体系统（如Deep Research）引入网络交互以缓解不确定性并减少错误。然而，现有研究多关注推理性能，忽视了智能体系统的效率问题。本文开展一项全面的实证研究，识别基于网页交互的智能体系统中的效率瓶颈。我们将端到端延迟分解为两大组件：LLM API延迟与网页环境延迟。在15个模型和5个服务商上进行广泛测试，发现基于API的智能体系统存在显著延迟差异。结果表明，网页环境延迟可占整体延迟高达53.7%。为降低延迟，我们提出SpecCache——一种结合推测执行的缓存框架。在两个标准基准上的大量评估显示，该方法相比随机缓存策略，缓存命中率最高提升58倍，网页环境开销减少最多3.2倍，且不损害智能体性能。
原文摘要 · Abstract (English)
Large Language Models (LLMs), such as OpenAI-o1 and DeepSeek-R1, have demonstrated strong reasoning capabilities. To further enhance LLM capabilities, recent agentic systems, such as Deep Research, incorporate web interactions into LLM reasoning to mitigate uncertainties and reduce potential errors. However, existing research predominantly focuses on reasoning performance, often neglecting the efficiency of agentic systems. In this work, we present a comprehensive empirical study that identifies efficiency bottlenecks in web-interactive agentic systems. We decompose end-to-end latency into two primary components: LLM API latency and web environment latency. We conduct a comprehensive empirical study across 15 models and 5 providers to demonstrate high variability in API-based agentic systems. We observe that web environment latency can contribute as much as 53.7% to the overall latency in a web-based agentic system. To improve latency, we propose SpecCache, a caching framework augmented with speculative execution that can reduce web environment overhead. Extensive evaluations on two standard benchmarks show that our approach improves the cache hit rate by up to 58x compared to a random caching strategy, while reducing web environment overhead by up to 3.2x, without degrading agentic system performance.
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。