运行时框架动态优化智能体任务执行，提升成功率与效率。
AI Runtime Infrastructure
- 在模型与应用之间构建可干预的运行时层
- 支持自适应内存管理与故障恢复，提升长流程可靠性
- 适合需要高可靠、低延迟的AI应用开发者
我们提出AI运行时基础设施，一个位于模型之上、应用之下的执行时层，能够实时观测、推理并干预智能体行为，以优化任务成功率、延迟、词元效率、可靠性和安全性。与模型级优化或被动日志系统不同，该基础设施将执行过程本身视为优化面，支持针对长周期智能体工作流的自适应内存管理、故障检测与恢复、策略执行。该架构使系统能够在运行时动态调整，显著提升复杂任务的执行质量。
原文摘要 · Abstract (English)
We introduce AI Runtime Infrastructure, a distinct execution-time layer that operates above the model and below the application, actively observing, reasoning over, and intervening in agent behavior to optimize task success, latency, token efficiency, reliability, and safety while the agent is running. Unlike model-level optimizations or passive logging systems, runtime infrastructure treats execution itself as an optimization surface, enabling adaptive memory management, failure detection, recovery, and policy enforcement over long-horizon agent workflows.
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。