---
title: "HiGram：具有路径级定位与重写的分层图记忆框架，提升LLM智能体长期推理"
source: "arXiv AI/CL/LG（论文）"
source_tier: "t2"
url: "https://arxiv.org/abs/2608.05095v1"
permalink: "https://feed.astralor.com/items/itm_6bea36a35954bc32ed63c9c6"
published: "2026-08-05T17:32:43.000Z"
score: 78
channel: "ai"
tags: ["HiGram","LLM智能体","分层图记忆","路径级改写"]
---

# HiGram：具有路径级定位与重写的分层图记忆框架，提升LLM智能体长期推理

## AI 点评

> 这篇论文值得所有做智能体记忆和长期推理的人关注。它的价值不在又造一个图记忆，而是把‘改哪里’和‘怎么改’一起解决了，直接减少记忆膨胀带来的检索成本。对做Agent产品的人尤其有用，因为长期对话中的冲突记忆是实际落地绕不开的坑。

## 速览

长期推理智能体需要随时间高效更新记忆。现有图记忆方法常将记忆存入扁平图，历史记忆积累会引入无关上下文，且更新时需逐单元重复改写。为此，HiGram提出演进式分层图记忆框架：用粗细粒度架构组织记忆以减少检索噪声；基于查询和更新条件化微图进行路径级定位，识别支持子图和证据路径；再通过协同改写方法联合修正单元内信息与单元间依赖。实验表明，该方法在长期对话问答和冲突感知记忆评估上显著提升答案质量与token效率，并在动态、静态和条件冲突场景下改善答案准确性与证据选择。

## 关键点

- 提出分层图记忆架构，将记忆组织为上层节点与MemoryUnit，降低检索时无关信息干扰
- 设计基于MicroGraph的路径级定位，在改写前识别支持子图与证据路径
- 提出协同改写方法，联合修正单元内记忆与单元间依赖关系，保持依赖结构有效更新
- 在长期对话问答及冲突感知评测中，答案质量与token效率均显著优于基线

## 全文

Agents for long term reasoning require a memory that can be efficiently and effectively updated over time, as new facts and external feedback continue to arrive. Recently, graph memory has been adopted to offer structural organization for multi-hop retrieval and reasoning. However, existing methods store all memories in a flat graph, and accumulated historical memories can introduce irrelevant contexts and increase the cost of evidence selection during retrieval. Moreover, they typically update memory units independently, requiring repeated unit-wise rewrite to cover related changes. To address these issues, we propose HiGram, an evolving hierarchical graph memory framework with path-level localization and rewriting. Specifically, we first propose a hierarchical graph memory, which organizes the memory into coarse-to-fine architecture composed of upper-level nodes and MemoryUnits, thereby reducing the amount of irrelevant information during retrieval. We further propose MicroGraph-based path-level localization, which leverages query and update conditioned MicroGraphs to identify support subgraph and evidence path before rewrite. Finally, we propose a coordinated rewriting method that jointly revises intra-unit memory and inter-unit dependencies, enable valid dependency structures updating in the localized evidence path. Experiments on benchmarks for long-term conversational question answering and conflict-aware memory evaluation demonstrate that our method demonstrate substantial improvements over baselines in answer quality and token efficiency. Besides, our method improves answer accuracy and query-valid evidence selection under dynamic, static, and conditional conflicts.

---

引用前请核对原文;本文由星际流动整理:https://feed.astralor.com/items/itm_6bea36a35954bc32ed63c9c6