HeMeR: Heterogeneous Memory Reconciliation for Embodied Agents via Structured KV Reuse
cs.AI
Submitted: 2026-11-12
Updated: 2026-11-12
Terminology
Sources
- Do As I Can, Not As I Say: Grounding Language in Robotic Affordances
- LRAgent: Efficient KV Cache Sharing for Multi-LoRA LLM Agents
- Efficient Multi-Adapter LLM Serving via Cross-Model KV-Cache Reuse with Activated LoRA
- MemOS: A Memory OS for AI System
- LMCache: An Efficient KV Cache Layer for Enterprise-Scale LLM Inference
- ALFWorld: Aligning Text and Embodied Environments for Interactive Learning
- MemRL: Self-Evolving Agents via Runtime Reinforcement Learning on Episodic Memory
- Memp: Exploring Agent Procedural Memory
- RPMS: Enhancing LLM-Based Embodied Planning through Rule-Augmented Memory Synergy
- Fast ECoT: Efficient Embodied Chain-of-Thought via Thoughts Reuse
- KEEP: A KV-Cache-Centric Memory Management System for Efficient Embodied Planning
- Improving the Serving Performance of Multi-LoRA Large Language Models via Efficient LoRA and KV Cache Management
- Qwen3-VL Technical Report
Related papers
- Multi-Objective Structured Pruning of LLMs for Latency and Model Size Optimization
- MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
- Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
- Embeddings for Preferences, Not Semantics
- Can We Trust Item Response Theory for AI Evaluation?
- Diagnosing Task Insensitivity in Language Agents