English(EN) COMPASS: Routing via Capability-Oriented Model Profiling with Adaptive Search, Selection, and Tool Use

新的COMPASS代理路由器优化LLM选择以降低成本和提高准确性

作者 PulseAugur 编辑部 · [1 个来源] · 2026-10-21 04:00

研究人员开发了COMPASS，一种新颖的代理LLM路由器，旨在优化模型选择以降低成本和提高准确性。与需要频繁更新的专用路由器不同，COMPASS使用LLM遵循路由配方，通过工具收集性能数据，甚至在选择模型之前检查候选答案。在LLMRouterBench和DeepSWE基准上的评估表明，与现有的路由方法相比，COMPASS以更低的成本实现了更高的准确性，并且无需重新训练即可适应新模型。 AI

影响这种代理路由方法可以通过优化模型选择，显著降低LLM部署的运营成本。

排序理由该集群包含一篇详细介绍LLM路由新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]

在 arXiv cs.AI 阅读 →

AI 生成摘要 · Google Gemini · 来自 1 个来源。我们如何撰写摘要 →

本文如何被排名

Signal score: 0 / 100; Composite score across the factors below. Higher = stronger signal that this story matters right now.
Newsworthiness bucket: Tool; 该集群包含一篇详细介绍LLM路由新方法的论文。[lever_c_demoted from research: ic=1 ai=1.0]
Source corroboration: Single-source cluster; Only one publisher covered this so far. Single-source stories can still rank when the publisher is high-authority, but they lack cross-source corroboration.
Topics: paper, infra; Editorial topic classification. Feeds into how the story surfaces on /topic/<slug> hub pages and into the per-entity coverage mix.
AI-industry relevance: High; Clearly on-topic for AI-industry coverage.
Story freshness: 4 days old; Aged out of breaking-news scoring windows; ranking reflects the durable signal from the full source set.

完整方法见我们的编辑标准。

报道来源 [1]

arXiv cs.AI TIER_1 English(EN) · Amin Rezaei, Pouya Parsa · 2026-10-21 04:00

COMPASS：通过面向能力的模型剖析进行路由，并结合自适应搜索、选择和工具使用

arXiv:2610.27822v1 Announce Type: new Abstract: LLM routing aims to select a capable model at low cost, but specialized routers can require updates as models and tasks change. We propose COMPASS, an agentic router in which an LLM follows a routing recipe, gathers performance and …

本文如何被排名

报道来源 [1]

COMPASS：通过面向能力的模型剖析进行路由，并结合自适应搜索、选择和工具使用

相关实体

相关话题