AgenticCache reuses cached plan transitions with asynchronous LLM refinement to raise embodied task success by 22% on average while cutting latency 65% and token use 50% across four benchmarks.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.LG 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
AgenticCache: Cache-Driven Asynchronous Planning for Embodied AI Agents
AgenticCache reuses cached plan transitions with asynchronous LLM refinement to raise embodied task success by 22% on average while cutting latency 65% and token use 50% across four benchmarks.