EvoGraph-Mem：面向长期语言智能体的故障感知可编辑图记忆
EvoGraph-Mem: Failure-Aware Editable Graph Memory for Long-Term Language Agents
浏览论文内容
中文总结 AI 辅助
本文针对长期语言智能体的记忆污染问题，提出故障感知可编辑图记忆框架，通过见解节点跟踪与图级编辑优化记忆，实验显示其性能优于现有记忆增强智能体基线。
中文摘要 AI 辅助
长期记忆对于在持续交互和不断变化的任务中运行的语言智能体至关重要。现有的记忆增强智能体主要关注存储和检索过往经验，但存储记忆的质量会随时间下降，特别是在新任务情境下，之前提炼的见解可能会过时、过度泛化或有害，在重复使用时会造成记忆污染。为解决该问题，本文研究长期语言智能体的见解级记忆维护，提出一种基于可编辑见解图的故障感知记忆维护框架。每个见解节点跟踪正证据、负证据和激活状态，使智能体能够区分可复用见解与冲突或无效见解。本文进一步引入实用感知检索机制和图控制器，在任务执行后通过保留可靠见解、归档无效见解、修订过时见解、添加新发现的可复用见解来更新记忆图。大量实验表明，在不同主干模型上，本文方法始终优于代表性的基于记忆的智能体基线。消融研究进一步证明，仅追加记忆不足以完成长周期任务，而证据感知检索和图级编辑可提升记忆可靠性和下游任务性能。
英文摘要
Long-term memory is essential for language agents operating across extended interactions and evolving tasks. Existing memory-augmented agents mainly focus on storing and retrieving past experience, but the quality of stored memories may degrade over time. In particular, previously distilled insights can become outdated, over-generalized, or harmful under new task contexts, causing memory pollution when repeatedly reused. To address this issue, we study insight-level memory maintenance for long-term language agents and propose a failure-aware memory maintenance framework based on an editable insight graph. Each insight node tracks positive evidence, negative evidence, and an activation state, enabling the agent to distinguish reusable insights from conflicting or invalid ones. We further introduce a utility-aware retrieval mechanism and a graph controller that updates the memory graph after task execution by keeping reliable insights, archiving invalid ones, revising outdated ones, and adding newly discovered reusable insights. Extensive experiments show that our method consistently outperforms representative memory-based agent baselines across different backbone models. Ablation studies further demonstrate that append-only memory is insufficient for long-horizon tasks, while evidence-aware retrieval and graph-level editing improve memory reliability and downstream task performance.
