AgenticCache: Cache-Driven Asynchronous Planning for Embodied AI Agents
For embodied AI agents, this work provides a practical method to reduce latency and cost while improving performance, though it is an incremental application of caching to a known bottleneck.
Embodied AI agents suffer from high latency and cost due to per-step LLM calls. AgenticCache reuses cached plans, improving task success rate by 22%, reducing simulation latency by 65%, and lowering token usage by 50% across 12 configurations.
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.