arXiv cs.CL· Zeru Shi, Jindong Jiang, Ryo Hachiuma, Yonggan Fu, Byung-Kwan Lee, Peter Belcak, Saurav Muralidharan, Ayush Agarwal, Ruixiang Tang, Ambrish Dantrey, Pavlo Molchanov, Anjul Patney, Subhashree Radhakrishnan·· 12 小时前AI 评分38
EdgeWise：通过选择性云端委派将长程智能体带到边缘端
EdgeWise: Bringing Long-Horizon Agents to the Edge via Selective Cloud Delegation
AI 导读
EdgeWise 是一个边缘-云协作框架，在本地设备部署 SLM 作为主求解器，仅在关键步骤将任务委派给云端 LLM。它采用步级强化学习联合优化任务求解与委派决策，在 SWE-Rebench 和 Terminal-Bench 2.1 上分别降低推理成本最高 62% 和 34%，性能与纯 LLM 执行相当或更优。
正文 · 原文
Authors:Zeru Shi, Jindong Jiang, Ryo Hachiuma, Yonggan Fu, Byung-Kwan Lee, Peter Belcak, Saurav Muralidharan, Ayush Agarwal, Ruixiang Tang, Ambrish Dantrey, Pavlo Molchanov, Anjul Patney, Subhashree Radhakrishnan
Abstract:Complex and long-horizon agent tasks often rely on frontier models deployed in the cloud to achieve strong performance. However, using these models for every step of a long-horizon trajectory incurs substantial inference cost, even though not all steps may require the same level of model capability. In this paper, we find that allocating the LLM to only a small subset of key steps can achieve performance comparable to full LLM execution while significantly reducing inference cost. Motivated by this observation, we propose EdgeWise, an edge-cloud collaboration framework that deploys an SLM on the local device as the primary solver and selectively delegates critical steps to a cloud LLM when stronger model capacity is needed. To enable autonomous delegation without additional models at inference time, we introduce a step-level RL method that jointly optimizes task solving and delegation, with fine-grained credit assignment for individual delegation decisions. We also introduce an external judge-based delegation strategy and use it to systematically investigate key design choices in edge-cloud collaboration, including when to delegate, how delegation decisions should be made, what context should be shared, and how frequently the cloud LLM should be invoked. Experiments show that EdgeWise matches or outperforms pure-LLM execution while reducing inference cost up to 62% on SWE-Rebench and 34% on Terminal-Bench 2.1. We further deploy EdgeWise on a local workstation, demonstrating comparable cost savings in a practical edge-cloud setting.
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.17560 [cs.CL] |
| (or arXiv:2610.17560v2 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.17560 arXiv-issued DOI via DataCite |
Submission history
From: Zeru Shi [view email]
[v1]
Tue, 13 Oct 2026 01:32:16 UTC (2,825 KB)
[v2]
Thu, 15 Oct 2026 22:39:12 UTC (2,825 KB)
来源：arXiv cs.CL · arxiv.org