# AgenticCache: Cache-Driven Asynchronous Planning for Embodied AI Agents

arXiv: https://arxiv.org/abs/2604.24039 · HTML: https://mlsanity.com/paper/2604.24039/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Multimodal and embodied agents, one of 16 directions in LLM agents and tool use.
- Builds on 29 of its 70 references that are in the map.
- First posted on arXiv 27 Apr 2026.

## Placed in

- LLM agents and tool use / [Multimodal and embodied agents](https://mlsanity.com/agents/multimodal-and-embodied-agents/)

## Builds on (most cited first, 29 of 29)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Efficient Memory Management for Large Language Model Serving with PagedAttention](https://mlsanity.com/paper/2309.06180/) (2023)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [Voyager: An Open-Ended Embodied Agent with Large Language Models](https://mlsanity.com/paper/2305.16291/) (2023)
- [MetaGPT: Meta Programming for A Multi-Agent Collaborative Framework](https://mlsanity.com/paper/2308.00352/) (2023)
- [MemGPT: Towards LLMs as Operating Systems](https://mlsanity.com/paper/2310.08560/) (2023)
- [Large Language Monkeys: Scaling Inference Compute with Repeated Sampling](https://mlsanity.com/paper/2407.21787/) (2024)
- [Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Heads](https://mlsanity.com/paper/2401.10774/) (2024)
- [ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Tasks](https://mlsanity.com/paper/1912.01734/) (2019)
- [TravelPlanner: A Benchmark for Real-World Planning with Language Agents](https://mlsanity.com/paper/2402.01622/) (2024)
- [SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verification](https://mlsanity.com/paper/2305.09781/) (2023)
- [ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulation](https://mlsanity.com/paper/2007.04954/) (2020)
- [Building Cooperative Embodied Agents Modularly with Large Language Models](https://mlsanity.com/paper/2307.02485/) (2023)
- [TEACh: Task-driven Embodied Agents that Chat](https://mlsanity.com/paper/2110.00534/) (2021)
- [OpenAGI: When LLM Meets Domain Experts](https://mlsanity.com/paper/2304.04370/) (2023)
- [Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AI](https://mlsanity.com/paper/2407.06886/) (2024)
- [BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulation](https://mlsanity.com/paper/2403.09227/) (2024)
- [MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Pool](https://mlsanity.com/paper/2406.17565/) (2024)
- [COMBO: Compositional World Models for Embodied Multi-Agent Cooperation](https://mlsanity.com/paper/2404.10775/) (2024)
- [Spectre Attacks: Exploiting Speculative Execution](https://mlsanity.com/paper/1801.01203/) (2018)
- [EPIC: Efficient Position-Independent Caching for Serving Large Language Models](https://mlsanity.com/paper/2410.15332/) (2024)
- [COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Models](https://mlsanity.com/paper/2409.15146/) (2024)
- [Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agents](https://mlsanity.com/paper/2506.14852/) (2025)
- [Odyssey: Empowering Minecraft Agents with Open-World Skills](https://mlsanity.com/paper/2407.15325/) (2024)
- [Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interface](https://mlsanity.com/paper/2410.00079/) (2024)
- [AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Execution](https://mlsanity.com/paper/2411.03519/) (2024)
- [On the Role of Temperature Sampling in Test-Time Scaling](https://mlsanity.com/paper/2510.02611/) (2025)
- [DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantization](https://mlsanity.com/paper/2412.20185/) (2024)
- [GainSight: A Unified Framework for Data Lifetime Profiling and Heterogeneous Memory Composition](https://mlsanity.com/paper/2504.14866/) (2025)

## Built on by (most cited first, 4 of 4)

- [Why Are GUI Agents Correct but Late? Decode on the Decision-Time Critical Path, Tested with Pre-Compiled Policy Trees](https://mlsanity.com/paper/2607.28399/) (2026)
- [GenCoord: Executable Commitments for Embodied LLM Agents under Private Information](https://mlsanity.com/paper/2608.22055/) (2026)
- [ChunkAct: Action Chunking for Agentic Robotics](https://mlsanity.com/paper/2610.18874/) (2026)
- [MIND: Instruction-Conditioned Incremental Grounding for Robots](https://mlsanity.com/paper/2610.19262/) (2026)

## Abstract (arXiv)

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.