OpenBMB 发布 EC²-Bench：研究边缘-云端协作执行智能体任务
OpenBMB 和清华做了个 EC²-Bench，测智能体任务到底该放端侧还是云端跑，结论是能省 85% 成本还保住七成性能，做端侧 Agent 的可以看看
OpenBMB 提出 EC²-Bench 基准，在 128 个可执行任务上对比四种边缘-云端协作策略。实验中 Qwen3.5-9B 端侧搭配 GLM-5.3 云端，最佳协作策略达到 60.46 分，为纯云端（82.70）的约 73%，成本仅 $8.73，约纯云端 $56.42 的 15%。在 Qwen3.7-Plus 上各策略完成任务差距缩到 3.67 分，隐私暴露差距却有 66.23 个百分点，且表现最好的策略泄露最多。研究还发现弱端侧（2B）适合让云端执行（Per-step Routing 得 39.97 vs 自委托 15.86），强端侧（9B）适合云端仅提建议的模式。
When should the cloud execute for the edge agent, and when should it just advise?
We present a systematic study of edge-cloud collaboration in long-horizon agent execution. Using EC²-Bench, we evaluate four collaboration strategies across 128 executable tasks, jointly measuring task completion, resource cost, and privacy exposure. Here are three key findings:
1️⃣ Small cloud budget, big gains.(cost-efficiency). With Qwen3.5-9B on-device and GLM-5.3 in the cloud, edge-only scores 39.12; the best collaboration reaches 60.46 — about 73% of cloud-only (82.70) — at only $8.73, roughly 15% of cloud-only's $56.42. 2️⃣ Performance converges, privacy doesn't. On Qwen3.7-Plus, best collaboration hits 76.84 vs 82.70 cloud-only; strategy gaps shrink to just 3.67 completion points, yet privacy exposure spans 66.23 percentage points — and the best-performing strategy leaks the most. 3️⃣ The mode flips with edge capability. Weak edges do best with an external router that lets the cloud execute (2B: Per-step Routing 39.97 vs self-delegation 15.86); stronger edges do best when the cloud only advises (9B Cloud Advisory 60.46). Further experiments highlight two abilities that matter for effective self-directed collaboration: knowing when to ask for help, and actually acting on the cloud's advice.
📄 Paper: https://t.co/ESc7nA1Aeu 🌐 Project: https://t.co/J1A3ZjtgCj 💻 Code: https://t.co/xjAuYnCDT1
#EdgeCloudCollaboration #AIAgent #LLM #OnDeviceAI #AgentBenchmark #EC2Bench #OpenBMB #Tsinghua
