---
title: "HKUST's AMA Framework Cuts AI Memory Costs by 80% Using Four Specialized Agents"
subtitle: "A four-agent memory framework aligns retrieval granularity with query intent, cutting token use by 80 percent while lifting long-context accuracy across benchmarks."
url: "https://alphasignal.ai/news/hkust-s-ama-framework-cuts-ai-memory-costs-by-80-using-four-specialized-agents"
author: "AlphaSignal Newsroom"
author_url: "https://alphasignal.ai/editorial-team"
company: "AlphaSignal"
company_url: "https://alphasignal.ai/company/alphasignal"
published: "2026-04-15T00:00:00.000Z"
updated: "2026-08-23T21:21:37.287Z"
type: "Paper"
topics:
  - "Agents"
  - "Retrieval"
subtopics:
  - "Memory"
  - "Multi Agent"
  - "Rag"
upvotes: 1501
source_url: "https://arxiv.org/abs/2601.20352"
comments: 0
truncated: true
---

# HKUST's AMA Framework Cuts AI Memory Costs by 80% Using Four Specialized Agents

> A four-agent memory framework aligns retrieval granularity with query intent, cutting token use by 80 percent while lifting long-context accuracy across benchmarks.

Long-running LLM agents keep hitting the same wall. Their memory systems either stuff everything into context, chunk it into rigid fixed-length blocks, or summarize it into blobs that lose the details needed for precise questions. A team from HKUST Guangzhou, Shandong University, NTU, and SUSTech has proposed a way out with [AMA (Adaptive Memory via Multi-Agent Collaboration)](https://arxiv.org/abs/2601.20352), a framework that treats memory management as a coordinated pipeline of four specialized agents rather than a single monolithic controller.

The headline result: AMA matches or beats state-of-the-art memory baselines while cutting token consumption by roughly 80 percent compared to full-context methods, and it reaches nearly 90 percent accuracy on knowledge-update tasks where facts change over time.

## The granularity dilemma

Existing agentic memory systems make a choice up front about how to store information, and then they live with it. Static approaches typically rely on fixed-length text chunking or coarse-grained summaries, which disrupts the semantic coherence of what gets stored. Coarse retrieval drags in noise. Fine-grained retrieval fragments logical dependencies. Neither scales cleanly across a mix of question types.

A second problem compounds over time. Most systems support create-read-update-delete on memory entries, but they lack a mechanism to detect when new information actually contradicts old information. Outdated facts pile up, and the agent starts confidently returning stale answers.

## Four agents, one memory lifecycle

AMA decomposes the memory pipeline into four roles that each do one thing well:

* **Constructor** turns raw dialogue into structured memory entries at three granularities.
* **Retriever** rewrites the query, classifies its intent, and routes it to the right granularity.

_Preview only. Full text requires an AlphaSignal Pro account._

## Sources

- [AMA: Adaptive Memory via Multi-Agent Collaboration (arXiv)](https://arxiv.org/abs/2601.20352)
- [AMA HTML full paper](https://arxiv.org/html/2601.20352)
- [Awesome AI Agent Papers 2026 (GitHub)](https://github.com/VoltAgent/awesome-ai-agent-papers)
- [LoCoMo benchmark](https://arxiv.org/abs/2402.17753)
- [LongMemEval benchmark](https://arxiv.org/abs/2410.10813)