让智能体自主管理记忆，减少冗余信息，提升长时任务表现。
MemPO: Self-Memory Policy Optimization for Long-Horizon Agents
- 智能体在交互中自动总结与管理记忆内容
- 相比基线模型，F1提升25.98，令牌消耗减少67.58%
- 适合需要长期决策的复杂任务场景
长时程智能体在与环境交互过程中面临上下文规模持续增长的问题，导致性能和稳定性下降。现有方法通常引入外部记忆模块并检索存储信息，但无法使模型主动管理记忆内容，也无法与整体任务目标对齐。为此，我们提出自记忆策略优化算法（MemPO），使智能体（策略模型）能够在交互过程中自主总结和管理其记忆。通过基于记忆有效性改进信用分配机制，策略模型可选择性保留关键信息，显著降低令牌消耗，同时保持任务性能。大量实验与分析表明，MemPO在基准模型上实现绝对F1分数提升25.98，在此前最优基线（SOTA）基础上提升7.1，同时令牌使用量减少67.58%和73.12%。代码已开源：https://github.com/TheNewBeeKing/MemPO。
原文摘要 · Abstract (English)
Long-horizon agents face the challenge of growing context size during interaction with environment, which degrades the performance and stability. Existing methods typically introduce the external memory module and look up the relevant information from the stored memory, which prevents the model itself from proactively managing its memory content and aligning with the agent's overarching task objectives. To address these limitations, we propose the self-memory policy optimization algorithm (MemPO), which enables the agent (policy model) to autonomously summarize and manage their memory during interaction with environment. By improving the credit assignment mechanism based on memory effectiveness, the policy model can selectively retain crucial information, significantly reducing token consumption while preserving task performance. Extensive experiments and analyses confirm that MemPO achieves absolute F1 score gains of 25.98 over the base model and 7.1 over the previous SOTA baseline, while reducing token usage by 67.58% and 73.12%. The code is released at https://github.com/TheNewBeeKing/MemPO.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。