Hierarchical Graph Memory for LLM Agents with Path-level Localization and Rewrite· 面向长期推理的层次图记忆框架
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 organiz
提出HiGram，改善图记忆的组织和更新机制，提高长期推理的效率和准确性。
- 核心方法
- 构建了一个具有路径级定位和重写功能的层次图记忆框架HiGram，能够更有效地组织和更新记忆。
- 适合谁读
- 研究者、工程师
- 要解决的问题
- 现有图记忆方法在处理累积历史记忆时引入无关上下文，增加证据选择成本，且更新机制效率低。
- 关键实验
- 通过与现有方法的对比实验，展示了HiGram在减少无关上下文和提高推理准确性方面的优势。
- 主要贡献
- 1) 设计了层次图记忆，减少无关上下文；2) 引入路径级定位和重写，提高更新效率和推理准确性。
- 意义与局限
- HiGram为长期推理任务提供了更高效的记忆管理机制，显著提高了任务处理能力和准确性，但在大规模动态数据环境下的性能仍需进一步验证。