The EvoGraph-Mem is a failure-aware editable graph memory framework for long-term language agents. Traditional memory-augmented agents mainly focus on storing and retrieving past experiences, 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 In particular, previously distilled insights can become outdated, over-generalized, or harmful under new task contexts, causing memory pollution when repeatedly reused.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that updates the memory graph after task execution by keeping reliable insights, archiving invalid ones, revising outdated ones, and adding newly discovered reusable insights.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. Blogger's Review: The EvoGraph-Mem framework significantly improves the memory quality and task performance of long-term language agents by introducing failure-aware and editable graph storage. This approach is crucial for handling long-time range tasks and avoiding memory pollution.