AMA: Adaptive Memory via Multi-Agent Collaboration

2026-01-28

AI Summary

This work addresses critical limitations in current large language model agents’ memory systems—namely, rigid retrieval granularity, redundant maintenance strategies, and coarse update mechanisms—which often lead to task-irrelevant information retrieval and logical inconsistencies. To overcome these issues, the authors propose a multi-agent collaborative adaptive memory framework featuring a hierarchical memory architecture and a multi-granularity construction mechanism that dynamically aligns retrieval granularity with task complexity. The framework incorporates adaptive query routing, consistency verification, and targeted refresh strategies to effectively mitigate memory redundancy and logical conflicts. It comprises four synergistic modules: Constructor, Retriever, Judge, and Refresher. Evaluated on long-context benchmarks, the system significantly outperforms existing approaches, reducing token consumption by approximately 80% while simultaneously improving retrieval accuracy and memory consistency.

Technology Category

• Multiagent Systems: Multiagent Learning
• Cognitive Modeling & Cognitive Systems: Agent Architectures
• Machine Learning: Large Multimodal Models (LMMs)

Application Category

• Search and Retrieval-Augmented AI: Agentic search
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions
• User Modeling, Personalization and Recommendation: Large Language Models (LLM) for user modeling and recommendation

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.

Problem

• LLM agents
• memory systems
• retrieval granularity
• logical inconsistency
• memory consistency

Innovation

• Adaptive Memory
• Multi-Agent Collaboration
• Hierarchical Memory
• Consistency Verification
• Granularity-aware Retrieval