Why does my background agent starve the user-facing one sharing the same infrastructure?
机会
When multiple AI agents run concurrently, some user-facing and some background, they compete for LLM inference capacity, context windows, and API rate limits with no priority ordering. Standard infrastructure schedulers are CPU and memory-aware but do not understand LLM workload semantics: which requests are mid-flight tool chains, which have irreversible side effects, and which can safely be preempted and resumed. The result is that a runaway background job starves a latency-sensitive user query and the only fix today is manual rate-limit tuning per deployment. The HiveMind paper proposes an OS-inspired approach but it is a research prototype with no production adoption and no standard interface for agent frameworks to build against.
为什么重要
An agent-aware workload scheduler is the missing infrastructure layer that makes multi-tenant LLM deployments as predictable as any other multi-process system.
我如何评估机会
机会评分是我的个人判断，而非量化指标：痛苦程度、发生频率，以及当前解决方案的匮乏程度。分数越高，意味着我认为越值得去构建。
出现时造成的痛苦程度。
人们实际遇到它的频率。
当前针对它的优质工具有多匮乏。