# AMV-L: Lifecycle-Managed Agent Memory for Tail-Latency Control in Long-Running LLM Systems

arXiv: https://arxiv.org/abs/2603.04443 · HTML: https://mlsanity.com/paper/2603.04443/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Placed in Agent memory systems, one of 16 directions in LLM agents and tool use.
- Builds on 13 of its 46 references that are in the map.
- First posted on arXiv 22 Feb 2026.

## Placed in

- LLM agents and tool use / [Agent memory systems](https://mlsanity.com/agents/agent-memory-systems/)

## Builds on (most cited first, 13 of 13)

- [ReAct: Synergizing Reasoning and Acting in Language Models](https://mlsanity.com/paper/2210.03629/) (2022)
- [Generative Agents: Interactive Simulacra of Human Behavior](https://mlsanity.com/paper/2304.03442/) (2023)
- [A-MEM: Agentic Memory for LLM Agents](https://mlsanity.com/paper/2502.12110/) (2025)
- [Efficiently Scaling Transformer Inference](https://mlsanity.com/paper/2211.05102/) (2022)
- [LongRAG: Enhancing Retrieval-Augmented Generation with Long-context LLMs](https://mlsanity.com/paper/2406.15319/) (2024)
- [MeMOTR: Long-Term Memory-Augmented Transformer for Multi-Object Tracking](https://mlsanity.com/paper/2307.15700/) (2023)
- [Long-Context Language Modeling with Parallel Context Encoding](https://mlsanity.com/paper/2402.16617/) (2024)
- [A Systematic Review of Key Retrieval-Augmented Generation (RAG) Systems: Progress, Gaps, and Future Directions](https://mlsanity.com/paper/2507.18910/) (2025)
- [Decoupled Context Processing for Context Augmented Language Modeling](https://mlsanity.com/paper/2210.05758/) (2022)
- [Accelerating Retrieval-Augmented Generation](https://mlsanity.com/paper/2412.15246/) (2024)
- [Time Aware Least Recent Used (TLRU) Cache Management Policy in ICN](https://mlsanity.com/paper/1801.00390/) (2018)
- [VectorLiteRAG: Latency-Aware and Fine-Grained Resource Partitioning for Efficient RAG](https://mlsanity.com/paper/2504.08930/) (2025)
- [Leaking Information Through Cache LRU States](https://mlsanity.com/paper/1905.08348/) (2019)

## Built on by (most cited first, 1 of 1)

- [Memory in the Loop: In-Process Retrieval as Extended Working Memory for Language Agents](https://mlsanity.com/paper/2607.05690/) (2026)

## Abstract (arXiv)

Long-running LLM agents require persistent memory to preserve state across interactions, yet most deployed systems manage memory with age-based retention (e.g., TTL). While TTL bounds item lifetime, it does not bound the computational footprint of memory on the request path: as retained items accumulate, retrieval candidate sets and vector similarity scans can grow unpredictably, yielding heavy-tailed latency and unstable throughput. We present AMV-L (Adaptive Memory Value Lifecycle), a memory-management framework that treats agent memory as a managed systems resource. AMV-L assigns each memory item a continuously updated utility score and uses value-driven promotion, demotion, and eviction to maintain lifecycle tiers; retrieval is restricted to a bounded, tier-aware candidate set that decouples the request-path working set from total retained memory. We implement AMV-L in a full-stack LLM serving system and evaluate it under identical long-running workloads against two baselines: TTL and an LRU working-set policy, with fixed prompt-injection caps. Relative to TTL, AMV-L improves throughput by 3.1x and reduces latency by 4.2x (median), 4.7x (p95), and 4.4x (p99), while reducing the fraction of requests exceeding 2s from 13.8% to 0.007%. Compared to LRU, AMV-L trades a small regression in median/p95 latency (+26% / +3%) for improved extreme-tail behavior (-15% p99; -98% >2s) and lower token overhead (approximately 6% fewer tokens/request), while matching retrieval quality (value means within approximately 0-2%). The gains arise primarily from bounding retrieval-set size and vector-search work, not from shortening prompts. Our results show that predictable performance for long-running LLM agents requires explicit control of memory working-set size and value-driven lifecycle management, rather than retention time alone.