arXiv cs.AI· Erle Zhu, Genrui Zhang, Keyang Hu, Mingyu Su, Hongning Wang·· 12 小时前AI 评分47
AOS-Bench：LLM 智能体能否管理动态工作负载？
AOS-Bench: Can LLM Agents Manage Dynamic Workloads?
AI 导读
新基准 AOS-Bench 将智能体系统作为工作负载管理器来评测：任务随时间陆续到达，需在共享 CPU 和内存限制下交付。在五组模型-harness 组合中，重负载下每个系统都损失 13 至 23 分；中等负载下各系统隔离成功率相差 11 分，但流式成功率相差 26 分。串行调度导致重负载下 73% 的任务无人认领，而固定并发度为 2 的策略在两个负载档位上均与最佳智能体管理策略相差不到 4 分。
正文
Abstract:Coding agents are moving from handling one request at a time to serving as persistent assistants to which users hand a stream of work: a build, a data-processing job and a bug fix may all be pending on the same machine at once. Such an agent must decide when to take on new tasks, how to delegate and overlap them, and how to stay within the machine's CPU and memory. Existing benchmarks cannot measure this, because they evaluate each task in isolation. We introduce \benchname{}, which evaluates an agent system as a workload manager: verified tasks arrive over time and must be delivered under shared CPU and memory limits, and the same tasks run one at a time serve as a per-system reference.
Across five model--harness pairs, isolated task success does not carry over evenly. On heavy workloads every system loses 13 to 23 points. On medium workloads, systems span 11 points in isolated success but 26 points in stream success, and two systems 0.6 points apart in isolation deliver 54\% and 68\% of the same tasks. Execution-policy interventions trace much of this gap to task intake: serial dispatch leaves 73\% of heavy-workload tasks unclaimed. Yet more elaborate management does not necessarily help. A fixed concurrency of two comes within four points of the best agent-managed policy on both medium and heavy workloads, and under every policy median CPU use stays below 30\% of the provisioned cores while tasks wait. These results identify workload management as a distinct capability for agents, and \benchname{} as a way to measure it.
| Subjects: | Artificial Intelligence (cs.AI) |
| Cite as: | arXiv:2610.33178 [cs.AI] |
| (or arXiv:2610.33178v1 [cs.AI] for this version) | |
| https://doi.org/10.48550/arXiv.2610.33178 arXiv-issued DOI via DataCite |
Submission history
From: Erle Zhu [view email]
[v1]
Fri, 23 Oct 2026 18:20:48 UTC (1,064 KB)
来源：arXiv cs.AI · arxiv.org