MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents

• URL: http://arxiv.org/abs/2605.03675v1
• Date: Tue, 05 May 2026 12:14:10 GMT
• Title: MEMTIER: Tiered Memory Architecture and Retrieval Bottleneck Analysis for Long-Running Autonomous AI Agents
• Abstract summary: We present MEMTIER, a tripartite memory architecture for the OpenClaw agent.<n>On the full LongMemEval-S benchmark, MEMTIER achieves Acc.382, F1=.412 with Qwen2.5-7B on a consumer 6GB GPU.<n>With DeepSeek-V4-Flash fact pre-population, single-session recall reaches 0.686-0.714, exceeding the paper's RAG GPT-4o on those categories.
• Score: 6.8552591401084015
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Long-running autonomous AI agents suffer from a well-documented memory coherence problem: tool-execution success rates degrade 14 percentage points over 72-hour operation windows due to four compounding failure modes in existing flat-file memory systems. We present MEMTIER, a tripartite memory architecture for the OpenClaw agent runtime that introduces a structured episodic JSONL store, a five-signal weighted retrieval engine, an attention-attributed cognitive weight update loop, an asynchronous consolidation daemon promoting episodic facts to a semantic tier, and a PPO-based policy framework for adapting retrieval weights (infrastructure validated; performance gains pending camera-ready). On the full 500-question LongMemEval-S benchmark (Wu et al., 2025), MEMTIER achieves Acc=0.382, F1=0.412 with Qwen2.5-7B on a consumer 6GB GPU - a +33 percentage point improvement over the full-context baseline (0.050 -> 0.382, i.e., 5% -> 38%). With DeepSeek-V4-Flash fact pre-population, single-session recall reaches 0.686-0.714, exceeding the paper's RAG BM25 GPT-4o baseline (0.560) on those categories. Temporal reasoning rises to 0.323 and multi-session synthesis to 0.173, demonstrating that structured semantic pre-population qualitatively changes what lightweight retrieval can achieve. All phases run locally on a consumer laptop with a 6GB GPU.

Related papers

• Deploying DeepSeek 175B Locally on a Single Consumer-Grade RTX 4060 Laptop with 32GB RAM for 200k-Scale Protein-Ligand Virtual Screening [2.2031237469592]
  Large language models (LLMs) have demonstrated exceptional performance in protein-ligand interaction prediction.<n>Recent advances in large language models (LLMs) have demonstrated exceptional performance in protein-ligand interaction prediction.
  arXiv  Detail & Related papers  (2026-08-31T14:35:56Z)
• On the Design of Qwen3.8-Next Architecture: Evaluation, Efficiency, and Training Stability [57.03393882933515]
  We describe the architecture and ablations of Qwen3.8-Flash-Next, a sparse mixture-of-experts model with 125B parameters, 6B activated per token, and 51B parameters of n-gram embedding tables held off the accelerator.<n>On fourteen pre-training benchmarks the model leads the 397B-A17B predecessor on eight and trails it on the rest by at most 2.6 points, at 1/3 the activated parameters, 1/3 the training tokens, and roughly 1/9 the training FLOPs.
  arXiv  Detail & Related papers  (2026-08-31T06:35:07Z)
• Anatomy of a Quantized Agent: VRAM Stability and Forecasting in Code-Synthesis Agentic Workloads [0.0]
  Analytical models of peak VRAM consumption for LLM inference decompose memory into weight-storage, KV-cache, and activation terms.<n>We evaluate this decomposition empirically within a strictly scoped measurement study.<n>We find no justification for deploying complex predictive VRAM models in highly quantized, weight-dominated regimes.
  arXiv  Detail & Related papers  (2026-08-15T08:39:43Z)
• LocalNav: Distilling Frontier VLMs and Embodied RL for On-Device Object Goal Navigation [53.88286427894783]
  Vision Language Models (VLMs) have emerged in the robotic domain as a powerful tool that enables environmental perception with language context.<n>Yet, their computational footprint typically confines them to cloud execution, hindering low-latency inference with local deployment on resource-constrained robots.<n>We present a distillation strategy that transfers complex spatial-semantic reasoning from large frontier models into a lightweight, 4B- parameter local VLM for edge execution on embedded GPU devices.
  arXiv  Detail & Related papers  (2026-06-26T09:11:59Z)
• FlashMemory-DeepSeek-V4: Lightning Index Ultra-Long Context via Lookahead Sparse Attention [77.12062766962815]
  Lookahead Sparse Attention (LSA) is powered by a Neural Memory Indexer built upon the DeepSeek-V4 architecture.<n>We instantiate this architecture via a backbone-free decoupled training strategy.<n>We show that FM-DS-V4 compresses the average physical KV cache footprint down to merely 13.5% of the full-context baseline.
  arXiv  Detail & Related papers  (2026-06-08T06:25:54Z)
• MEME: Multi-entity & Evolving Memory Evaluation [76.57263966646404]
  MEME defines six tasks spanning the full space defined by the multi-entity and evolving axes.<n> evaluating six memory systems spanning three memory paradigms on 100 controlled episodes.<n>We find that all systems collapse on dependency reasoning under the default configuration.
  arXiv  Detail & Related papers  (2026-05-12T17:55:10Z)
• ZenBrain: A Neuroscience-Inspired 7-Layer Memory Architecture for Autonomous AI Systems [51.56484100374058]
  On LongMemEval-500, ZenBrain matches a long-context oracle's binary-judge accuracy to within 4.5 pp.<n> ZenBrain is a 7-layer neuroscience-inspired memory architecture.
  arXiv  Detail & Related papers  (2026-04-26T20:39:19Z)
• Predictive Multi-Tier Memory Management for KV Cache in Large-Scale GPU Inference [0.0]
  Key-value ( KV) cache memory management is the primary bottleneck in large-scale GPU inference serving.<n>Current systems suffer from three compounding inefficiencies.<n>We present a unified system that addresses all three problems.
  arXiv  Detail & Related papers  (2026-04-19T21:34:09Z)
• MemMachine: A Ground-Truth-Preserving Memory System for Personalized AI Agents [2.541923091180284]
  Large Language Model (LLM) agents require persistent memory to maintain personalization, factual continuity, and long-horizon reasoning.<n>We present MemMachine, an open-source memory system that integrates short-term, long-term episodic, and profile memory.<n>MemMachine uses contextualized retrieval that expands nucleus matches with surrounding context, improving recall when relevant evidence spans multiple dialogue turns.
  arXiv  Detail & Related papers  (2026-04-06T16:57:06Z)
• SuperLocalMemory V3.3: The Living Brain -- Biologically-Inspired Forgetting, Cognitive Quantization, and Multi-Channel Retrieval for Zero-LLM Agent Memory Systems [0.0]
  We present SuperLocalMemory V3.3 ("The Living Brain"), a local-first agent memory system.<n>It implements the full cognitive memory taxonomy with mathematical lifecycle dynamics.<n>It is open source under the Elastic License 2.0, runs entirely on CPU, and has over 5,000 monthly downloads.
  arXiv  Detail & Related papers  (2026-04-06T08:27:26Z)
• Omni-SimpleMem: Autoresearch-Guided Discovery of Lifelong Multimodal Agent Memory [76.63021613850093]
  We deploy an autonomous research pipeline to discover Omni-SimpleMem, a unified multimodal memory framework for lifelong AI agents.<n>System achieves state-of-the-art on two benchmarks, improving F1 by +411% on LoCoMo and +214% on Mem-Gallery.<n>We provide a taxonomy of six discovery types and identify four properties that make multimodal memory particularly suited for autoresearch.
  arXiv  Detail & Related papers  (2026-04-01T15:06:23Z)
• Resource-Efficient Iterative LLM-Based NAS with Feedback Memory [49.44875022114861]
  Neural Architecture Search (NAS) automates network design, but conventional methods demand substantial computational resources.<n>We propose a closed-loop pipeline leveraging large language models (LLMs) to iteratively generate, evaluate, and refine convolutional neural network architectures.
  arXiv  Detail & Related papers  (2026-03-12T16:00:22Z)
• A Dynamic Retrieval-Augmented Generation System with Selective Memory and Remembrance [0.0]
  We introduce emph Adaptive RAG Memory (ARM), a retrieval-augmented generation (RAG) framework that replaces a static vector index with a emphdynamic memory substrate.<n>ARM reaches near state-of-the-art performance on a lightweight retrieval benchmark.<n>ARM yields competitive accuracy, self-regularizing memory growth, and interpretable retention dynamics without retraining the generatorcolorblack and provides practical trade-off between quality, latency and memory efficiency for production and research RAG system.
  arXiv  Detail & Related papers  (2026-01-04T21:51:41Z)
• MEM1: Learning to Synergize Memory and Reasoning for Efficient Long-Horizon Agents [84.62985963113245]
  We introduce MEM1, an end-to-end reinforcement learning framework that enables agents to operate with constant memory across long multi-turn tasks.<n>At each turn, MEM1 updates a compact shared internal state that jointly supports memory consolidation and reasoning.<n>We show that MEM1-7B improves performance by 3.5x while reducing memory usage by 3.7x compared to Qwen2.5-14B-Instruct on a 16-objective multi-hop QA task.
  arXiv  Detail & Related papers  (2025-06-18T19:44:46Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.