微软发布智能体上下文压缩新方法
微软的FOCUS方法能智能压缩智能体上下文，大幅减少内存占用同时提升任务成功率，特别适合处理长对话场景。
微软提出FOCUS方法，解决智能体随交互历史增长性能下降的问题。该方法通过识别并保留与决策相关的历史单元，丢弃无关内容。在工具调用、问答、网页搜索和多轮对话基准测试中，FOCUS能将峰值上下文减少高达48%，任务成功率提升最高8.9分。无需训练数据或微调，可作为独立层应用于闭源API模型。
New paper from Microsoft on compressing agent context at test time.
If your agent gets worse as its interaction history grows, this method is worth a look.
FOCUS asks which past interactions the agent's next decisions actually depend on. It keeps those units of the history and drops the others. It needs no training data or fine-tuning, so it works as a separate layer in front of closed-API models.
On tool-calling, QA, web and multi-turn dialogue benchmarks, it cuts peak context by up to 48% and raises task success by up to 8.9 points compared with running on the full history.
Paper: https://t.co/nl7pGmNcYP
