Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution
Empowering Edge Agents: A Systematic Analysis of Edge-Cloud Collaboration in LLM Agent Execution
EC2-Bench 評估長時程 LLM 智能體執行中的邊緣—雲端協作,涵蓋任務表現、資源使用及私隱暴露。研究發現,協作能在三者之間取得較佳平衡;邊緣模型能力越強,越適合採用由邊緣端主導的協作方式。程式碼及資源已開放。
Published on Oct 13
Authors:
,
,
,
,
,
,
Abstract
EC2-Bench evaluates edge-cloud collaboration for long-horizon LLM agents, revealing trade-offs among performance, resource use, and privacy, and showing that stronger edge models favor more edge-controlled collaboration.
Edge-cloud collaboration combines the lower inference overhead and greater data locality of edge-side execution with the stronger capabilities of cloud-hosted models. However, as LLM agents increasingly operate in long-horizon scenarios, cloud participation becomes interleaved throughout execution rather than a one-shot decision for each query. Such interleaved participation introduces trajectory-level effects that remain insufficiently understood. To address this gap, we introduce EC2-Bench, a benchmark for evaluating edge-cloud collaboration in long-horizon agent execution. It provides executable digital-workspace agent tasks and a unified evaluation framework covering task performance, resource usage, and privacy exposure. Using this benchmark, we empirically study diverse forms of edge-cloud collaboration. Our study reveals three findings. First, collaboration achieves a favorable balance among task performance, resource usage, and privacy exposure compared with edge-only and cloud-only execution. Second, as edge models become stronger, collaborative execution approaches cloud-only performance, and performance differences across strategies shrink, while privacy exposure remains strongly strategy-dependent. Third, stronger edge capability shifts preferred collaboration from externally controlled cloud participation and direct cloud execution toward more edge-controlled collaboration. Further analyses identify cloud-invocation decision-making and instruction following as important edge-side abilities for effective collaboration. These findings provide a systematic understanding of edge-cloud collaboration in long-horizon agent execution and insights for designing future edge agents that effectively collaborate with cloud models. Code and resources are available at https://github.com/OpenBMB/EC2-Bench.
View arXiv page View PDF Project page GitHub Add to collection
Get this paper in your agent:
hf papers read 2610.17816
Don't have the latest CLI?
curl -LsSf https://hf.co/cli/install.sh | bash
Models citing this paper 0
No model linking this paper
Cite arxiv.org/abs/2610.17816 in a model README.md to link it from this page.
Datasets citing this paper 1
chengpingan/EC2-Bench
Viewer • Updated 2 days ago • 128 • 78 • 1
Spaces citing this paper 0
No Space linking this paper
Cite arxiv.org/abs/2610.17816 in a Space README.md to link it from this page.
Collections including this paper 1
來源:HuggingFace Daily Papers(社區熱門論文) · huggingface.co