用缓存复用计划，让智能体少调大模型，提速降本
AgenticCache: Cache-Driven Asynchronous Planning for Embodied AI Agents
- 基于计划局部性，缓存常用动作序列避免重复调用大模型
- 平均提升任务成功率22%，仿真延迟降低65%，令牌消耗减少50%
- 适合需要低延迟、低成本的多智能体场景，如机器人协作
具身智能体越来越依赖大语言模型（LLMs）进行规划，但每步调用大模型带来严重延迟和成本。本文发现具身任务具有强计划局部性，即下一步计划可从当前计划高度预测。基于此，我们提出AgenticCache：一种规划框架，通过复用缓存的计划避免每步调用大模型。每个智能体在运行时查询频繁计划转移的缓存，而后台的Cache Updater异步调用大模型验证并优化缓存条目。在四个多智能体具身基准测试中，AgenticCache在12种配置（4个基准×3个模型）下平均提升任务成功率22%，仿真延迟降低65%，令牌使用量减少50%。基于缓存的计划复用为低延迟、低代价的具身智能体提供了实用路径。代码已公开于https://github.com/hojoonleokim/MLSys26_AgenticCache。
原文摘要 · Abstract (English)
Embodied AI agents increasingly rely on large language models (LLMs) for planning, yet per-step LLM calls impose severe latency and cost. In this paper, we show that embodied tasks exhibit strong plan locality, where the next plan is largely predictable from the current one. Building on this, we introduce AgenticCache, a planning framework that reuses cached plans to avoid per-step LLM calls. In AgenticCache, each agent queries a runtime cache of frequent plan transitions, while a background Cache Updater asynchronously calls the LLM to validate and refine cached entries. Across four multi-agent embodied benchmarks, AgenticCache improves task success rate by 22% on average across 12 configurations (4 benchmarks x 3 models), reduces simulation latency by 65%, and lowers token usage by 50%. Cache-based plan reuse thus offers a practical path to low-latency, low-cost embodied agents. Code is available at https://github.com/hojoonleokim/MLSys26_AgenticCache.
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。