1
华硕 ROG 魔盒 Pro Max 电竞路由器开售：BE12000、双万兆，最低到手 3199 元
IT之家 5 月 25 日消息，华硕 ROG 魔盒 Pro Max 游戏电竞路由器今晚 20:00 正式开售， 到手价 4055 元 ， P LUS 会员补贴到手价 3199 元 。 京东 华硕（ASUS）ROG 魔盒 Pro Max 万兆路由器 4055 元 直达链接 这款路由器配置双 10G 口…
2
How does an AI agent pick from 686 skills in a second?
实测AI代理如何在一秒内从686个技能中精准选中最优解，准确率68%的秘密武器是语义路由+向量检索。
I ran an empirical test on the "skills as semantic router" pattern for Claude Code agents. I indexed 686 randomly sampled skills from a 4,556-skill co…
3
Ex-GraphRAG: Interpretable Evidence Routing for Graph-Augmented LLMs
新型图增强LLM框架Ex-GraphRAG，通过可解释证据路由解决GNN编码器节点贡献纠缠问题。
arXiv:2605.21994v1 Announce Type: cross Abstract: GraphRAG conditions language models on subgraphs retrieved from knowledge graphs, encoded via messag…
4
2099 元，中兴 G5 Pro 高性能版 5G 移动路由器 CPE 将于 5 月 28 日开售
IT之家 5 月 22 日消息，中兴 G5 Pro 高性能版 5G 移动路由器 CPE 将于 5 月 28 日开售，支持 5G-A 超高速网络。这款新品已开启预售，价格为 2099 元。 IT之家从商品页面获悉，这款 CPE 支持 Wi-Fi 7， 理论峰值下载速度可达 4.29Gbps ；内置中兴…
5
GL.iNet 推出三频 BE10000 旅行无线路由器 Slate 7 Pro
IT之家 5 月 22 日消息， GL.iNet （广联智通）本月 19 日推出三频 Wi-Fi 7 旅行无线路由器 Slate 7 Pro (GL-BE10000)。广联智通宣称这是 首款实现三频 Wi-Fi 聚合的同类产品 ，拥有可与全尺寸家用路由器媲美的性能。 Slate 7 Pro 三维 1…
6
Show HN: Aisbf, a self-hostable OpenAI-compatible AI proxy/router
自托管OpenAI兼容AI代理/路由器，测试期仅€2/月享受无限Pro访问，性价比极高。
AISBF is a self-hostable AI proxy/router that exposes an OpenAI-compatible API while letting you route across different providers and model pools. I b…
7
Building APIs with Next.js
Next.js官方博客手把手教你用App Router构建API，涵盖路由处理、动态路由、中间件等实战要点。
Learn about how to build APIs with Next.js.
8
Dr.LLM: Dynamic Layer Routing in LLMs
提出动态层路由机制，让LLM推理时跳过无关层，显著提升效率与精度。
arXiv:2510.12773v2 Announce Type: replace-cross Abstract: Large Language Models (LLMs) process every token through all layers of a transformer stack, …
9
HyDRA: Hybrid Dynamic Routing Architecture for Heterogeneous LLM Pools
针对异构LLM池的混合动态路由架构，无需因模型目录变更而重训练，解决现有二元路由的耦合问题。
arXiv:2605.17106v1 Announce Type: cross Abstract: Production LLM deployments increasingly maintain heterogeneous model pools spanning order-of-magnitu…
10
UCCI: Calibrated Uncertainty for Cost-Optimal LLM Cascade Routing
提出基于校准不确定度的LLM级联路由方案，在保持性能的同时降低推理成本。
arXiv:2605.18796v1 Announce Type: new Abstract: LLM cascades and model routing promise lower inference cost by sending easy queries to a small model a…
11
The Scaling Laws of Skills in LLM Agent Systems
首次揭示LLM代理系统中技能缩放定律，基于15个模型、超百万数据点的实证研究
arXiv:2605.16508v1 Announce Type: new Abstract: As agent systems scale, skills accumulate into large reusable libraries, yet their scaling laws remain…
12
Helping Customers in Distress: An LLM-powered Agent that Converses, Probes, and Routes
银行每年处理数百万份欺诈报告，这个AI代理通过对话、探询和智能路由，精准分流客户至专家团队，解决人工流程慢和压力大的痛点。
arXiv:2605.16268v1 Announce Type: cross Abstract: Banks receive millions of reports of fraud, scams, and disputed transactions every year, making it c…
13
Show HN: Llama-dash – local LLM operators dashboard and proxy
本地LLM运维仪表板，集成路由、日志、监控，轻松管理多个模型上游。
Article URL: https://github.com/ndom91/llama-dash Comments URL: https://news.ycombinator.com/item?id=48196202 Points: 1 # Comments: 0
14
R2V Agent: Teaching SLMs When to Ask for Help
教你如何让小型语言模型学会判断何时该“求救”，避免盲目依赖昂贵大模型，提升Agent系统效率的突破性研究。
arXiv:2605.16604v1 Announce Type: new Abstract: Efficient agentic systems should incur expensive frontier-model costs only on decisions where a cheape…
15
Nuxt 3.13
Nuxt 3.13 发布，新增路由组、岛屿组件头部管理和自定义预取，组织路由更灵活。
Nuxt 3.13 is out - porting back some of the new features we're building for Nuxt 4!
16
L2R: Low-Rank and Lipschitz-Controlled Routing for Mixture-of-Experts
创新MoE路由方法，结合低秩分解与Lipschitz控制提升专家专化性和模型性能。
arXiv:2601.21349v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) models scale neural networks by conditionally activating a small su…
17
Mixture of Experts for Low-Resource LLMs
揭秘低资源语言大模型中的专家路由：对比Transformer与Mamba混合架构的MoE表现。
arXiv:2605.17598v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures enable efficient model scaling, yet expert routing behavior acr…
18
BEAM: Binary Expert Activation Masking for Dynamic Routing in MoE
一种新型动态路由方法通过二进制专家激活掩码减少MoE冗余计算，无需重训即可加速推理。
arXiv:2605.14438v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures enhance the efficiency of large language models by activating o…
19
LogRouter: Adaptive Two-Level LLM Routing for Log Question Answering in Big Data Systems
生产日志问答新方案：LogRouter实现自适应双层LLM路由，降低资源消耗。
arXiv:2605.18015v1 Announce Type: new Abstract: Production log analytics in self-hosted, resource-constrained environments requires natural-language a…
20
I Cut My LLM API Bill by 73% — Here's the Exact Optimization Playbook
73%的LLM API成本削减实战策略，从路由层到缓存策略，无需降低质量即可实现。
I Cut My LLM API Bill by 73% — Here's the Exact Optimization Playbook Running LLMs in production burns cash. Fast. When your app goes from "prototype"…