HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse
HeMeR is an inference framework for embodied agents that reconciles key-value cache states across declarative, procedural, and working memory as those contents change during interaction. Instead of reprocessing each updated memory context as new input, it preserves KV states for unchanged memory and recomputes only the parts affected by updates. The authors evaluate it on ALFWorld, Habitat, and real-world robotic deployments. In the real-world setting, they report 83.20% task success and a reduction in per-step inference time from 2.94 to 1.87 seconds compared with MemRL.
It offers a concrete efficiency technique for LLM-based embodied agents, with reported latency and task-success results that are useful to researchers and builders working on memory-heavy agent inference.
Comments & Questions (0)
No comments yet
Be the first to comment!