mlsanityData to 7 Oct 2026

AgenticCache: Cache-Driven Asynchronous Planning for Embodied AI Agents

arXiv 2604.24039 ↗First posted 27 Apr 2026cs.LG cs.AI cs.CLcited by 2

On the map: LLM agents and tool use → Multimodal and embodied agents

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.

Key facts. Cited by 2 papers in the map (data through 7 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.

Builds on

29 of 70 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024COMBO: Compositional World Models for Embodied Multi-Agent Cooperation16 Apr

Other references · 28

  1. 2022ReAct: Synergizing Reasoning and Acting in Language Modelscited by 8,355
  2. 2023Efficient Memory Management for Large Language Model Serving with PagedAttentioncited by 5,767
  3. 2023Generative Agents: Interactive Simulacra of Human Behaviorcited by 3,500
  4. 2023Voyager: An Open-Ended Embodied Agent with Large Language Modelscited by 2,081
  5. 2023MetaGPT: Meta Programming for A Multi-Agent Collaborative Frameworkcited by 1,761
  6. 2023MemGPT: Towards LLMs as Operating Systemscited by 1,295
  7. 2024Large Language Monkeys: Scaling Inference Compute with Repeated Samplingcited by 946
  8. 2024Medusa: Simple LLM Inference Acceleration Framework with Multiple Decoding Headscited by 821
  9. 2019ALFRED: A Benchmark for Interpreting Grounded Instructions for Everyday Taskscited by 773
  10. 2024TravelPlanner: A Benchmark for Real-World Planning with Language Agentscited by 385
  11. 2023SpecInfer: Accelerating Generative Large Language Model Serving with Tree-based Speculative Inference and Verificationcited by 359
  12. 2020ThreeDWorld: A Platform for Interactive Multi-Modal Physical Simulationcited by 249
16 more
  1. 2023Building Cooperative Embodied Agents Modularly with Large Language Modelscited by 231
  2. 2023OpenAGI: When LLM Meets Domain Expertscited by 196
  3. 2021TEACh: Task-driven Embodied Agents that Chatcited by 194
  4. 2024Aligning Cyber Space with Physical World: A Comprehensive Survey on Embodied AIcited by 175
  5. 2024BEHAVIOR-1K: A Human-Centered, Embodied AI Benchmark with 1,000 Everyday Activities and Realistic Simulationcited by 140
  6. 2024MemServe: Context Caching for Disaggregated LLM Serving with Elastic Memory Poolcited by 67
  7. 2018Spectre Attacks: Exploiting Speculative Executioncited by 47
  8. 2024EPIC: Efficient Position-Independent Caching for Serving Large Language Modelscited by 45
  9. 2024COHERENT: Collaboration of Heterogeneous Multi-Robot System with Large Language Modelscited by 43
  10. 2024Odyssey: Empowering Minecraft Agents with Open-World Skillscited by 26
  11. 2025Agentic Plan Caching: Test-Time Memory for Fast and Cost-Efficient LLM Agentscited by 23
  12. 2024Interactive Speculative Planning: Enhance Agent Efficiency through Co-design of System and User Interfacecited by 15
  13. 2024AI Metropolis: Scaling Large Language Model-based Multi-Agent Simulation with Out-of-order Executioncited by 14
  14. 2025On the Role of Temperature Sampling in Test-Time Scalingcited by 10
  15. 2024DecDEC: A Systems Approach to Advancing Low-Bit LLM Quantizationcited by 7
  16. 2025GainSight: A Unified Framework for Data Lifetime Profiling and Heterogeneous Memory Compositioncited by 1

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026Why Are GUI Agents Correct but Late? Decode on the Decision-Time Critical Path, Tested with Pre-Compiled Policy Treescited by 0
  2. 2026GenCoord: Skill-Path Commitments under Private Informationcited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Mosaic: Runtime-Efficient Multi-Agent Embodied Planning
  2. 2025Robotouille: An Asynchronous Planning Benchmark for LLM Agents
  3. 2026KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning
  4. 2026Embodied Task Planning via Graph-Informed Action Generation with Large Language Models
  5. 2024LoTa-Bench: Benchmarking Language-oriented Task Planners for Embodied Agents
  6. 2026TypeGo: An OS Runtime for Embodied Agents
  7. 2026Learning Agent Execution for KV-Cache Management in Agentic Serving
  8. 2025Reflex First, Reflect Later: Latency-Aware Embodied LLM Agents for Dynamic Response