AMA: Adaptive Memory via Multi-Agent Collaboration

TL;DR

AMA introduces a multi-agent hierarchical memory system for LLMs that dynamically manages retrieval granularity, improves long-term memory consistency, and reduces token usage significantly.

Contribution

It presents a novel multi-agent framework with hierarchical memory management, adaptive retrieval, and consistency enforcement for LLMs, addressing limitations of existing rigid memory approaches.

Findings

AMA outperforms state-of-the-art baselines on long-context benchmarks.

Reduces token consumption by approximately 80% compared to full-context methods.

Effectively maintains retrieval precision and memory consistency over time.

Abstract

The rapid evolution of Large Language Model (LLM) agents has necessitated robust memory systems to support cohesive long-term interaction and complex reasoning. Benefiting from the strong capabilities of LLMs, recent research focus has shifted from simple context extension to the development of dedicated agentic memory systems. However, existing approaches typically rely on rigid retrieval granularity, accumulation-heavy maintenance strategies, and coarse-grained update mechanisms. These design choices create a persistent mismatch between stored information and task-specific reasoning demands, while leading to the unchecked accumulation of logical inconsistencies over time. To address these challenges, we propose Adaptive Memory via Multi-Agent Collaboration (AMA), a novel framework that leverages coordinated agents to manage memory across multiple granularities. AMA employs a hierarchical memory design that dynamically aligns retrieval granularity with task complexity. Specifically, the Constructor and Retriever jointly enable multi-granularity memory construction and adaptive query routing. The Judge verifies the relevance and consistency of retrieved content, triggering iterative retrieval when evidence is insufficient or invoking the Refresher upon detecting logical conflicts. The Refresher then enforces memory consistency by performing targeted updates or removing outdated entries. Extensive experiments on challenging long-context benchmarks show that AMA significantly outperforms state-of-the-art baselines while reducing token consumption by approximately 80% compared to full-context methods, demonstrating its effectiveness in maintaining retrieval precision and long-term memory consistency.